# How Lineaje Policies Protect ### Stage 1 - AI Reconnaissance **Primary Goal of Adversary**: Understand how the AI behaves **Core Attack Surface**: Prompts, responses, refusals
Policy NameAI BOM ImpactedHow Lineaje Implements This Policy
Use only LLMs from the organization’s approved list. See: AI_APP_SEC_006LLM, AI AgentRestricts model usage to vetted LLMs, reducing the ability to probe or select models with weaker controls or governance.
Do not use LLMs from the organization's disallowed list. See: AI_APP_SEC_028LLM, AI AgentPrevents reconnaissance, probing, or control attempts using unapproved or high-risk LLMs.
MCP clients must log all interactions with the MCP server. See: AI_APP_SEC_022MCP ServerEnables visibility into probing, boundary testing, and exploratory interactions without preventing them.
Do not send PII to LLMs. See: AI_DAT_SEC_011AI AgentRemoves sensitive personal data from early AI interaction, limiting information exposure during exploratory use.
Mask PII on user interfaces. See: AI_DAT_SEC_012AI AgentLimits observable sensitive data that could be inferred or harvested during initial interaction.
Agent must log all interactions with the LLM. See: AI_APP_SEC_035LLM, AI AgentProvides detection and forensic evidence of reconnaissance behavior without blocking it.
### Stage 2 - Trust Establishment and Manipulation **Primary Goal of Adversary**: Make the AI assume legitimacy **Core Attack Surface**: Language, tone, authority cues
Policy NameAI BOM ImpactedHow Lineaje Implements This Policy
Use only LLMs from the organization’s approved list. See: AI_APP_SEC_006LLM, AI AgentReduces implicit trust in unvetted models.
Do not use LLMs from the organization's disallowed list. See: AI_APP_SEC_028LLM, AI AgentPrevents trust in risky or malicious LLM endpoints.
MCP client must authenticate the MCP server. See: AI_IAC_002MCP Server, AI AgentPrevents rogue servers from establishing false legitimacy and injecting trusted responses.
MCP server must authenticate the client. See: AI_IAC_006LLM, AI AgentPrevents unauthorized or spoofed clients from gaining trusted access.
Inter-agent communication must be authenticated. See: AI_IAC_007AI AgentReduces implicit trust between agents and prevents impersonation.
### Stage 3 - Instruction and Input Weaponization **Primary Goal of Adversary**: Deliver hidden malicious intent **Core Attack Surface**: Prompts, documents, RAG inputs
Policy NameAI BOM ImpactedHow Lineaje Implements This Policy
Do not allow malicious content via hidden prompts. See: AI_APP_SEC_001LLM, AI AgentBlocks hidden instructions from being interpreted as executable intent.
Do not allow malicious content via prompts encoded in Base64. See: AI_APP_SEC_002LLM, AI AgentPrevents decoding and execution of obfuscated instructions.
Do not allow malicious content via hidden prompts written in leetspeak. See: AI_APP_SEC_032LLM, AI AgentStops obfuscation-based bypass of input filters.
MCP server must validate and sanitize all input. See: AI_APP_SEC_014MCP ServerStops weaponized input at ingress.
LLM must validate and sanitize any input before processing. See: AI_APP_SEC_038LLMPrevents malicious input from influencing reasoning.
### Stage 4 - Reasoning-Time Execution **Primary Goal of Adversary**: Change the AI’s goal or logic **Core Attack Surface**: Planning and reasoning process
Policy NameHow Lineaje Implements This Policy
MCP server must not interact directly with an LLM. See: AI_APP_SEC_033LLM, MCP ServerPrevents unsafe reasoning execution at the server layer.
Do not allow malicious content via hidden prompts. See: AI_APP_SEC_001LLM, AI AgentReduces likelihood of reasoning hijack.
Agent must validate, sanitize LLM output including for presence of eval or any dynamic code execution primitive in LLM output. See: AI_APP_SEC_029AI AgentLimits unsafe reasoning outputs.
### Stage 5 - Tool and Environment Interaction **Primary Goal of Adversary**: Act on real systems **Core Attack Surface**: Tools, APIs, plugins, workflows
Policy NameAI BOM ImpactedHow Lineaje Implements This Policy
Agent must validate, sanitize LLM output including for presence of eval or any dynamic code execution primitive in LLM output. See: AI_APP_SEC_029AI AgentLimits unsafe reasoning outputs.
Limit agent credentials to a maximum of three external systems. See: AI_IAC_008AI AgentPrevents credential sprawl and limits unauthorized privilege escalation.
### Stage 6 - Privilege Escalation **Primary Goal of Adversary**: Gain more authority **Core Attack Surface**: Context, credentials, delegation
Policy NameAI BOM ImpactedHow Lineaje Implements This Policy
Do not store secrets in code. See: AI_DAT_SEC_001LLM, AI Agent, MCP ServerEliminates durable credential discovery.
Limit agent credentials to a maximum of three external systems. See: AI_IAC_008AI AgentPrevents credential sprawl and limits unauthorized privilege escalation.
MCP server must not interact directly with an LLM. See: AI_APP_SEC_033LLM, MCP ServerPrevents implicit privilege delegation.
### Stage 7 - Lateral Movement **Primary Goal of Adversary**: Spread the compromise **Core Attack Surface**: Agents, workflows, shared memory
Policy NameAI BOM ImpactedHow Lineaje Implements This Policy
Client must validate and sanitize any output from an MCP server. See: AI_APP_SEC_023AI Agent, MCP ClientBreaks trust transitivity between services.
Inter-agent communication must be authenticated. See: AI_IAC_007AI AgentPrevents agent impersonation and propagation.
Mask PII on user interfaces. See: AI_DAT_SEC_012LLM, AI AgentPrevents visual propagation of sensitive data.
### Stage 8 - Persistence **Primary Goal of Adversary**: Make the compromise survive **Core Attack Surface**: Memory, RAG, feedback, training
Policy NameAI BOM ImpactedHow Lineaje Implements This Policy
Do not log PII. See: AI_DAT_SEC_010LLM, AI Agent, MCP ServerPrevents durable storage of sensitive data.
Do not send PII to LLMs. See: AI_DAT_SEC_011MCP ServerPrevents PII from entering persistent AI state.
MCP clients must log all interactions with the MCP server. See: AI_APP_SEC_022MCP ServerEnables detection of persistent behavior.
Agents must log all interactions with the LLM. See: AI_APP_SEC_035LLM, AI AgentSupports forensic investigation.
### Stage 9 - Command & Control **Primary Goal of Adversary**: Maintain influence over time **Core Attack Surface**: Normal interaction, schedules
Policy NameAI BOM ImpactedHow Lineaje Implements This Policy
Clear exit or termination criteria must exist for the agent to consider its task complete and stop executing. See: AI_APP_SEC_034AI AgentPrevents sustained or looping agent control.
MCP clients must log all interactions with the MCP server. See: AI_APP_SEC_022MCP ServerEnables detection of persistent behavior.
Agents must log all interactions with the LLM. See: AI_APP_SEC_035LLM, AI AgentSupports forensic investigation.
### Stage 10 - Actions on Objectives **Primary Goal of Adversary**: Cause business impact **Core Attack Surface**: Outputs, integrations, downstream systems
Policy NameHow Lineaje Implements This Policy
Encrypt PII when shared. See: AI_DAT_SEC_009LLM, AI Agent, MCP ServerPrevents usable data disclosure.
Agent must validate, sanitize LLM output including for presence of eval or any dynamic code execution primitive in LLM output. See: AI_APP_SEC_029AI AgentReduces likelihood of high-impact actions.
### Lineaje Policies ### AI Threats and Exploits
AI_APP_SEC_001 Do not allow malicious content via hidden prompts - Critical **Violation Summary** Hidden or non-visible prompts detected in the system introduce risks of prompt injection, bypass of safety controls, and untraceable model behavior. **Affected Assets** * LLM * AI Agent **Technical Details** Hidden prompts introduce several risks including: * Undetectable prompt injection * Unpredictable, unsafe or incorrect output * Bypass safety and governance controls * Unsafe or inconsistent agent behavior * Regulatory and Ethical exposure **Attack Vector**: Prompt **Attack Complexity**: Low **Privileges Required**: None **User Interaction**: None **Confidentially Impact**: High **Integrity Impact**: High **Availability Impact**: Low **Framework** * **Nov 18, 2024 - OWASP-LLM**: LLM01, LLM02, LLM04, LLM08 * **March 2025 - OWASP-ASI**: ASI-01, ASI-04, ASI-07, ASI-09 * **Aug 1, 2024 - EU AI Act**: 1.11, 2.12, 3.13, 4.50 **References**
AI_APP_SEC_002 Do not allow malicious content via encoded prompts - Critical **Violation Summary** Encoded prompts are instructions hidden inside obfuscated text, Base64, hex, zero-width characters, steganographic patterns, metadata, or structured payloads. They allow attackers or internal actors to bypass oversight, evade filters, or manipulate an AI system without detection. **Affected Assets** * LLM * AI Agent **Technical Details** Hidden prompts introduce several risks including: * Invisible prompt injection leading to unauthorized system behavior * Safety bypass (toxicity, policy evasion, jailbreaks) * Leakage of sensitive data or internal system instructions * Corruption of downstream workflows due to manipulated outputs * Violations of transparency, record-keeping, and explainability requirements **Attack Vector**: Prompt **Attack Complexity**: Low **Privileges Required**: None **User Interaction**: None **Confidentially Impact**: High **Integrity Impact**: High **Availability Impact**: Low **Framework** * **Nov 18, 2024 - OWASP-LLM**: LLM01, LLM04, LLM05, LLM08 * **March 2025 - OWASP-ASI**: ASI-01, ASI-04, ASI-07, ASI-09 * **Aug 1, 2024 - EU AI Act**: 1.11, 2.12, 3.13, 4.50 **References**
AI_APP_SEC_006 Use only LLMs from the organization’s approved list – High/Critical **Violation Summary** \ Using an LLM that is not on the organization’s approved list introduces uncontrolled security, privacy, compliance, and operational risks. Unapproved LLMs may have unknown data handling practices, insufficient security controls, unclear training or retention policies, weak contractual protections, or unvetted model behavior. This bypasses governance, procurement, and risk management processes, exposing the organization to data leakage, regulatory violations, vendor lock-in, and unpredictable AI behavior across agentic and automated workflows. **Affected Assets** * LLM * AI Agent **Technical Details** Using an unapproved LLM introduces several risks including: * Uncontrolled processing, retention, or reuse of sensitive data and prompts * Unknown security posture, access controls, and logging practices * Potential training on proprietary or regulated data without consent * Incompatibility with organizational guardrails, monitoring, or audit tooling * Increased exposure to prompt injection, data leakage, or unsafe outputs * Breach of contractual, legal, or regulatory obligations * Loss of centralized governance, visibility, and incident response capability **Attack Vector**: LLM selection / API usage outside approved platforms \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None \ **Confidentiality Impact**: Critical \ **Integrity Impact**: High \ **Availability Impact**: Medium (instability or service changes) **Frameworks** **Nov 18, 2024 – OWASP-LLM**: LLM03, LLM05, LLM08 \ **March 2025 – OWASP-ASI**: ASI-04, ASI-05, ASI-09, ASI-12 \ **Aug 1, 2024 – EU AI Act**: Articles 11, 12, 13, 50, obligations for GPAI risk management and provider accountability **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_APP_SEC_014 MCP server must validate and sanitize all input - Critical **Violation Summary** If an MCP server accepts input from clients, agents, or LLMs without validation or sanitization, it becomes vulnerable to malformed payloads, injection attacks, unauthorized tool invocation, unsafe command execution, and data corruption. Because MCP servers often expose high-privilege operations (file access, API calls, system actions), unvalidated input can be weaponized to manipulate workflows, escalate privileges, or deliver malicious instructions that compromise both the server environment and downstream systems. **Affected Assets** MCP Server **Input Validation** Validation ensures that input conforms to expected structure, type, length, format, and policy constraints before it is processed by the LLM. It answers the question if the input is allowed to be processed. **Examples of Validation** * Rejecting prompts longer than a defined maximum length * Enforcing schema compliance (e.g., JSON with specific fields only) * Blocking inputs containing disallowed patterns (e.g., ignore previous instructions, system override) * Restricting input sources to authenticated or trusted origins * Ensuring prompts match an approved task or intent category **Input Sanitization** Sanitization transforms input to remove, neutralize, or normalize unsafe elements while preserving legitimate intent. Sanitization ensures that the input is made safe before processing. **Examples of Sanitization** * Normalizing Unicode to remove obfuscation (e.g., leetspeak, homoglyphs) * Stripping zero-width or invisible characters * Decoding and inspecting encoded content (Base64, hex) before use * Escaping or isolating untrusted text so it cannot be interpreted as instructions * Removing or redacting sensitive data (PII, secrets) **Technical Details** Not validating or sanitizing MCP server input introduces several risks including: * Injection of malicious commands, payloads, or structured data into tools or system functions * Execution of unsafe or hallucinated instructions originating from LLM output * Unauthorized access or misuse of server-side capabilities and sensitive APIs * Corruption of data, resources, or operational workflows through malformed input * Increased attack surface for prompt-to-system escalation attacks * Loss of governance, auditability, and explainability of server-driven actions * Violations of integrity, safety, and regulatory obligations for high-risk functions **Attack Vector**: MCP client → server input channel \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None \ **Confidentiality Impact**: High \ **Integrity Impact**: Critical \ **Availability Impact**: Medium to High (depending on server capabilities) **Timeline** * **Nov 18, 2024 – OWASP-LLM**: LLM01 (Prompt/Instruction Injection), LLM04 (Behavior Manipulation), LLM05 (Sensitive Information Disclosure), LLM06 (Hallucination Risks), LLM08 (Transparency & Audit Failures) * **March 2025 – OWASP-ASI**: ASI-01 (Input/Output Integrity), ASI-05 (Safe Handling), ASI-07 (Reliability), ASI-09 (Traceability), ASI-12 (Operational Monitoring) * **Aug 1, 2024 – EU AI Act**: Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), plus Annex III robustness & safety requirements **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_APP_SEC_022 MCP clients must log all interactions with the MCP server - Critical **Violation Summary**\ A missing or incomplete logging mechanism between the MCP client and MCP server creates a critical visibility and governance gap. MCP interactions often trigger high-privilege actions (tool execution, data access, workflow modification). Without proper logs, misuse, anomalies, attacks, or unauthorized system changes cannot be detected, investigated, or attributed. This results in opaque AI behavior, broken audit trails, and non-compliance with required traceability and transparency obligations. **Affected Assets** * MCP Client * MCP Server **Technical Details** Failure to log MCP interactions introduces several risks including: * Undetectable misuse or abuse of MCP server tools * Inability to perform forensic investigation during an incident * Loss of accountability for AI-driven actions and decisions * Exposure to covert prompt injection or unauthorized system manipulation * Violations of traceability, transparency, and record-keeping requirements * Difficulty detecting anomalous behavior or lateral movement * Corruption of downstream workflows due to hidden actions **Attack Vector:** MCP tool invocation / API interaction\ **Attack Complexity:** Low\ **Privileges Required:** None, when exploited via LLM-driven tool calls.\ **User Interaction:** None\ **Confidentiality Impact:** High\ **Integrity Impact:** High\ **Availability Impact:** Low **Framework** **Nov 18, 2024 – OWASP-LLM:** LLM01, LLM04, LLM05, LLM08\ **March 2025 – OWASP-ASI:** ASI-01, ASI-04, ASI-07, ASI-09\ **Aug 1, 2024 – EU AI Act:** 1.11, 2.12, 3.13, 4.50 **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_APP_SEC_023 Client must validate and sanitize any output from a MCP server - Critical **Violation Summary** When an MCP client consumes output from an MCP server without validation or sanitization, it exposes the AI system and downstream components to malformed data, malicious payloads, injection attacks, hallucinated instructions, and unsafe tool execution. MCP server output may include structured data, commands, untrusted text, or model-generated content. Without safeguards, unvalidated output can drive unsafe automated actions, corrupt workflows, or leak sensitive information. **Affected Assets** * AI Agent * MCP Client **Input Validation** Validation ensures that input conforms to expected structure, type, length, format, and policy constraints before it is processed by the LLM. It answers the question if the input is allowed to be processed. **Examples of validation** * Rejecting prompts longer than a defined maximum length * Enforcing schema compliance (e.g., JSON with specific fields only) * Blocking inputs containing disallowed patterns (e.g., ignore previous instructions, system override) * Restricting input sources to authenticated or trusted origins * Ensuring prompts match an approved task or intent category **Input Sanitization** Sanitization transforms input to remove, neutralize, or normalize unsafe elements while preserving legitimate intent. Sanitization ensures that the input is made safe before processing. **Examples of sanitization** * Normalizing Unicode to remove obfuscation (e.g., leetspeak, homoglyphs) * Stripping zero-width or invisible characters * Decoding and inspecting encoded content (Base64, hex) before use * Escaping or isolating untrusted text so it cannot be interpreted as instructions * Removing or redacting sensitive data (PII, secrets) **Affected Assets** * AI Agent * MCP Client **Technical Details** Lack of output validation introduces several risks including: * Execution of harmful or unintended actions triggered by malformed MCP output * Injection of unsafe code, commands, or control sequences into downstream systems * Propagation of hallucinated, incorrect, or manipulated data * Leakage of sensitive information through unfiltered server responses * Corruption of business workflows or agent decision chains * Evasion of safety controls due to unmonitored tool responses * Violations of auditability, reliability, and compliance requirements **Attack Vector**: MCP response / server-generated output \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None \ **Confidentiality Impact**: High \ **Integrity Impact**: High \ **Availability Impact**: Medium (via cascading workflow corruption) **Timeline** * **Nov 18, 2024** – OWASP-LLM: LLM01, LLM03, LLM04, LLM06, LLM08 * **March 2025** – OWASP-ASI: ASI-01, ASI-05, ASI-07, ASI-09 * **Aug 1, 2024** – EU AI Act: 1.11, 2.12, 3.13, 4.50 **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_APP_SEC_028 Do not use LLMs from the organization's disallowed list - Critical **Violation Summary** \ Using an LLM that is explicitly on the organization’s block list represents a deliberate bypass of governance, security, and risk controls. Block-listed LLMs are typically prohibited due to known deficiencies such as unsafe data handling, unacceptable training or retention practices, lack of contractual protections, regulatory exposure, weak security posture, or demonstrated unsafe behavior. Their use introduces severe security, privacy, compliance, and reputational risks and undermines centralized AI governance. **Affected Assets** * LLM * AI Agent **Technical Details** Using a block-listed LLM introduces several risks including: * Known or previously identified data leakage, retention, or misuse risks * Exposure of sensitive, proprietary, or regulated data to untrusted providers * Circumvention of organizational security, legal, and compliance controls * Lack of auditability, logging, or incident response visibility * Increased likelihood of unsafe, biased, or non-compliant model behavior * Breach of regulatory, contractual, or internal policy obligations * Loss of trust in AI governance and enforcement mechanisms **Attack Vector**: Unauthorized LLM selection / direct API or UI usage \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None \ **Confidentiality Impact**: Critical \ **Integrity Impact**: High \ **Availability Impact**: Medium **Frameworks** * **Nov 18, 2024 – OWASP-LLM**: LLM03, LLM05, LLM08 * **March 2025 – OWASP-ASI**: ASI-04, ASI-05, ASI-09, ASI-12 * **Aug 1, 2024 – EU AI Act**: Articles 11, 12, 13, 50, GPAI risk-management and provider accountability requirements **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_APP_SEC_029 Agent must validate, sanitize LLM output including for presence of eval or any dynamic code execution primitive in LLM output - Critical **Affected Assets** AI Agent **Violation Summary** When LLM outputs are consumed without validation or sanitization, the system becomes vulnerable to unsafe instructions, hallucinated commands, malicious payloads, and untrusted code. This risk becomes critical when the LLM output may contain eval, shell commands, SQL statements, or other dynamic execution primitives. If such outputs pass directly into an interpreter, agent tool, or workflow engine, they can lead to arbitrary code execution, data exfiltration, workflow corruption, or full system compromise. **Input Validation** Validation ensures that input conforms to expected structure, type, length, format, and policy constraints before it is processed by the LLM. It answers the question if the input is allowed to be processed. **Examples of Validation** * Rejecting prompts longer than a defined maximum length * Enforcing schema compliance (e.g., JSON with specific fields only) * Blocking inputs containing disallowed patterns (e.g., ignore previous instructions, system override) * Restricting input sources to authenticated or trusted origins * Ensuring prompts match an approved task or intent category **Input Sanitization** Sanitization transforms input to remove, neutralize, or normalize unsafe elements while preserving legitimate intent. Sanitization ensures that the input is made safe before processing. **Examples of Sanitization** * Normalizing Unicode to remove obfuscation (e.g., leetspeak, homoglyphs) * Stripping zero-width or invisible characters * Decoding and inspecting encoded content (Base64, hex) before use * Escaping or isolating untrusted text so it cannot be interpreted as instructions * Removing or redacting sensitive data (PII, secrets) **Affected Assets** AI Agent **Technical Details** Failure to validate LLM output introduces several risks including: * Accidental or malicious execution of model-generated code (e.g., eval, exec, Function, subprocess calls) * Injection of harmful commands or payloads into tools, agents, or downstream applications * Execution of hallucinated instructions that modify resources, corrupt data, or trigger destructive operations * Leakage of internal or sensitive information through improperly filtered responses * Exploitation of agents that automatically convert LLM output into actions (“AI code injection”) * Loss of safety, explainability, reliability, and auditability in automated pipelines * Violations of governance, logging, and traceability requirements **Attack Vector**: LLM output → downstream interpreter / agent tool \ **Attack Complexity**: Low (LLM can be tricked into generating dangerous primitives) \ Privileges Required: None \ **User Interaction**: None (fully autonomous execution paths are most at risk) \ **Confidentiality Impact**: High \ **Integrity Impact**: Critical \ **Availability Impact**: Medium to High **Timeline** * **Nov 18, 2024 – OWASP-LLM**: LLM01, LLM03, LLM04, LLM06, LLM08 * **March 2025 – OWASP-ASI**: ASI-01, ASI-05, ASI-07, ASI-09, ASI-12 * **Aug 1, 2024 – EU AI Act**: 1.11, 2.12, 3.13, 4.50 **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_APP_SEC_032 Do not allow malicious content via hidden prompts written in leetspeak - High/Critical **Violation Summary** \ Allowing prompts written in leetspeak (e.g., h4x0r, 3v4l, 1nj3ct, byp4ss) or similar obfuscated language enables attackers to evade input validation, safety filters, and policy enforcement mechanisms. Leetspeak transforms malicious intent into visually altered but semantically equivalent text, allowing prompt injection, jailbreak attempts, encoded instructions, and policy bypasses to slip past keyword-based detection and moderation layers. This weakens the integrity and reliability of LLM-driven systems, especially in agentic and autonomous workflows. **Affected Assets** * LLM * AI Agent **Technical Details** Allowing leetspeak introduces several risks including: * Bypass of keyword-based safety, moderation, and policy filters * Injection of malicious or unsafe instructions disguised as benign input * Increased success of encoded or obfuscated prompt attacks * Manipulation of agent reasoning or tool invocation logic * Reduced auditability and explainability due to obfuscated intent * Amplification of downstream risks when leetspeak-generated outputs drive actions **Attack Vector**: LLM input prompt (user, agent, or external system) \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None (especially in automated or agent-driven scenarios) \ **Confidentiality Impact**: High \ **Integrity Impact**: High to Critical \ **Availability Impact**: Low **Reference Frameworks** * **Nov 18, 2024 – OWASP-LLM**: LLM01, LLM04, LLM06, LLM08 * **March 2025 – OWASP-ASI**: ASI-01, ASI-04, ASI-07, ASI-09), ASI-12 * **Aug 1, 2024 – EU AI Act**: Articles 11, 12, 13, 50, plus Annex III robustness and risk-management requirements **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_APP_SEC_033 MCP server must not directly interact with the LLM – Critical **Violation Summary**\ When an MCP server directly interacts with the LLM—rather than operating only through an authenticated, validated, policy-enforcing MCP client—it collapses the trust boundary between system capabilities and untrusted model output. This allows the LLM to influence, manipulate, or trigger server-side actions without authorization or validation. Direct LLM-to-server interaction bypasses safety controls, authentication layers, input validation, output filtering, logging standards, and audit requirements. This exposes the environment to unbounded prompt injection, unsafe tool execution, data leakage, and full-system compromise. **Affected Assets** * LLM * MCP Server **Technical Details**\ Allowing an MCP server to directly interact with an LLM introduces several risks including: * Execution of unsafe, hallucinated, or malicious LLM-generated instructions on high-privilege server tools * Prompt injection attacks gaining direct access to server capabilities * Bypassing client-side authentication, authorization, validation, and logging layers * Data leakage through uncontrolled LLM requests or responses * Inability to enforce least-privilege and zero-trust boundaries between model and system operations * Loss of auditability because actions occur without the MCP client as an intermediary * Violations of governance, safety, and regulatory obligations for high-risk AI systems **Attack Vector:** LLM output → server action path\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** High\ **Integrity Impact:** Critical\ **Availability Impact:** Medium to High **Framework** * **Nov 18, 2024 – OWASP-LLM:** LLM01 (Prompt/Instruction Injection), LLM04 (Behavior Manipulation), LLM05 (Data Disclosure), LLM06 (Hallucination Risks), LLM08 (Transparency & Audit Failures) * **Mar 2025 – OWASP-ASI:** ASI-01 (Input/Output Integrity), ASI-04 (Governance), ASI-05 (Safe Handling), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug 1, 2024 – EU AI Act:** Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), plus Annex III robustness & safety controls for high-risk systems **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_APP_SEC_034 Clear exit or termination criteria must exist for the agent to consider its task complete and stop executing – High/Critical **Violation Summary**\ When an AI agent is not given explicit, enforceable exit or termination criteria, it may continue executing indefinitely, escalate actions beyond intended scope, repeatedly invoke tools, consume excessive compute, or enter unsafe operational loops. Lack of defined stopping conditions increases the risk of runaway behavior, unintended system modifications, resource exhaustion, privacy violations, and unbounded interaction with external systems or MCP tools. Agents without termination logic become unpredictable, ungovernable, and potentially harmful. **Affected Assets** AI Agent **Technical Details**\ Missing termination criteria introduces several risks including: * Infinite or runaway task execution that triggers unnecessary or harmful actions * Repeated tool invocation (MCP or external APIs), leading to data exposure or workflow corruption * Accidental escalation of privileges as the agent searches endlessly for ways to complete the task * Hallucination-driven decisions due to self-reinforcing reasoning loops * Excessive resource consumption or uncontrolled cost * Increased attack surface for prompt injection that pushes the agent into unsafe recursive behavior * Violations of safety, oversight, and accountability requirements **Attack Vector:** Agent reasoning cycle / task execution loop\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** Medium to High (depending on tool access)\ **Integrity Impact:** High\ **Availability Impact:** Medium to High **Framework** * **Nov 18, 2024 – OWASP-LLM**: LLM01 (Injection), LLM04 (Behavior Manipulation), LLM06 (Hallucination Risks), LLM08 (Transparency & Audit Failures) * **Mar 2025 – OWASP-ASI**: ASI-01 (Integrity), ASI-04 (Governance), ASI-07 (Reliability), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug 1, 2024 – EU AI Act**: Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), Annex III requirements for safe, predictable operation of high-risk systems **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_APP_SEC_035 Agents must log all interactions with the LLM - Critical **Violation Summary**\ If agents do not log their interactions with the LLM, including prompts, responses, tool requests, and reasoning triggers, organizations lose visibility into how decisions were made, what data was exchanged, and whether harmful or unauthorized actions occurred. Missing LLM interaction logs break auditability, hinder incident response, obscure the source of incorrect or unsafe outputs, and prevent compliance verification. Lack of logging also enables attackers to exploit the agent–LLM channel without detection. **Affected Assets** * LLM * AI Agent **Technical Details**\ Not logging agent ↔LLM interactions introduces several risks including: * Inability to reconstruct how the agent reached a decision or triggered an action * Loss of forensic evidence needed for incident response or regulatory review * Undetected prompt injection, harmful outputs, or unsafe tool invocations * Unmonitored leakage of sensitive data or PII through prompts or responses * Difficulty identifying hallucination-driven failures or behavioral drift * Loss of traceability required for governance, transparency, and safety assurance * Violations of logging, documentation, and accountability requirements **Attack Vector:** Agent ↔ LLM communication channel\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** High\ **Integrity Impact:** High\ **Availability Impact:** Low **Framework** * **Nov 18, 2024 – OWASP-LLM**: LLM01 (Injection), LLM03 (Data Leakage), LLM04 (Behavior Manipulation), LLM08 (Transparency & Audit Failures) * **Mar 2025 – OWASP-ASI**: ASI-01 (Integrity), ASI-05 (Data Handling), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug 1, 2024 – EU AI Act**: Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), with Annex III traceability requirements for high-risk systems **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_APP_SEC_038 The LLM must validate and sanitize any input before processing - Critical **Violation Summary** When a Large Language Model (LLM) accepts input without proper validation and sanitization, it becomes highly susceptible to prompt injection, encoded or hidden instructions, malicious payloads, and adversarial manipulation. Unsanitized inputs—originating from users, agents, tools, MCP servers, or external systems—can override system instructions, bypass guardrails, contaminate reasoning, and trigger unsafe downstream actions. This risk is amplified in agentic and tool-enabled environments where LLM output directly influences real systems. **Affected Assets** LLM **Input Validation** Validation ensures that input conforms to expected structure, type, length, format, and policy constraints before it is processed by the LLM. It answers the question if the input is allowed to be processed. **Examples of Validation** * Rejecting prompts longer than a defined maximum length * Enforcing schema compliance (e.g., JSON with specific fields only) * Blocking inputs containing disallowed patterns (e.g., ignore previous instructions, system override) * Restricting input sources to authenticated or trusted origins * Ensuring prompts match an approved task or intent category **Input Sanitization** Sanitization transforms input to remove, neutralize, or normalize unsafe elements while preserving legitimate intent. Sanitization ensures that the input is made safe before processing. **Examples of Sanitization** * Normalizing Unicode to remove obfuscation (e.g., leetspeak, homoglyphs) * Stripping zero-width or invisible characters * Decoding and inspecting encoded content (Base64, hex) before use * Escaping or isolating untrusted text so it cannot be interpreted as instructions * Removing or redacting sensitive data (PII, secrets) **Affected Assets** LLM **Technical Details** Failure to validate and sanitize LLM input introduces several risks including: * Prompt injection that overrides system and developer intent * Encoded, obfuscated, or hidden instructions bypassing safety controls * Injection of malicious content that manipulates tool usage or agent behavior * Leakage of sensitive data caused by adversarial prompt construction * Hallucination amplification driven by malformed or hostile inputs * Propagation of unsafe or untrusted instructions to downstream systems * Loss of transparency, auditability, and policy enforcement across AI workflows **Attack Vector**: LLM input channel (user, agent, tool, MCP, external system) \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None (especially in autonomous or agent-driven flows) \ **Confidentiality Impact**: High \ **Integrity Impact**: Critical \ **Availability Impact**: Medium **Timeline** * **Nov 18, 2024 – OWASP-LLM**: LLM01 (Prompt Injection), LLM04 (Model Behavior Manipulation), LLM05 (Sensitive Information Disclosure), LLM08 (Insufficient Transparency & Auditability) * **March 2025 – OWASP-ASI**: ASI-01 (Input Integrity), ASI-04 (Governance), ASI-07 (Reliability), ASI-09 (Traceability), ASI-12 (Operational Monitoring) * **Aug 1, 2024 – EU AI Act**: Articles 11 (Technical Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), plus Annex III robustness, safety, and risk-management requirements **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_APP_SEC_039 Sanitize and validate all input to the AI Model - Critical **Violation Summary** \ If input sent to an LLM is not validated and sanitized, the system becomes vulnerable to prompt injection, obfuscated or encoded instructions, malformed payloads, and adversarial manipulation. Unchecked inputs originating from users, agents, tools, uploaded files, MCP services, or external systems can override system intent, bypass safety controls, contaminate reasoning, and trigger unsafe downstream actions. This risk is amplified in agentic, tool-enabled, and autonomous workflows where LLM output directly influences real systems. **Affected Assets** * LLM * AI Agent **Technical Details** Failure to validate and sanitize input before sending it to an LLM introduces several risks including: * Prompt injection that overrides system and developer intent * Encoded, hidden, or obfuscated instructions (Base64, leetspeak, zero-width characters) bypassing guardrails * Injection of malicious content that manipulates tool usage or agent behavior * Leakage of sensitive data caused by adversarial prompt construction * Hallucination amplification driven by malformed or hostile inputs * Propagation of unsafe or untrusted instructions to downstream systems * Loss of transparency, auditability, and policy enforcement across AI workflows **Attack Vector**: Input channel → LLM (user, agent, tool, file ingestion, MCP, external system) \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None (especially in autonomous or agent-driven flows) \ **Confidentiality Impact**: High \ **Integrity Impact**: Critical \ **Availability Impact**: Medium **Framework** * OWASP-LLM: LLM01, LLM04, LLM05, LLM08 * OWASP-ASI: ASI-01 (Input Integrity), ASI-04, ASI-07, ASI-09, ASI-12 * EU AI Act: Articles 11, 12, 13, 50, plus Annex III robustness, safety, and risk-management requirements **References** \ \
AI_APP_SEC_040 Do not allow malicious content via prompts included in uploaded files – Critical **Violation Summary** \ If uploaded files (documents, PDFs, spreadsheets, images with OCR, code files, logs) are ingested by an LLM or agent without inspection for malicious prompts, attackers can embed hidden, encoded, or context-manipulating instructions that influence model behavior. These “prompt-in-files” attacks allow adversaries to bypass input controls, poison agent reasoning, extract sensitive data, or trigger unauthorized tool actions—often without any visible user prompt. **Affected Assets** AI Agent **Technical Details** Failing to scan uploaded files for malicious prompts introduces several risks including: * Hidden prompt injection embedded in document text, comments, metadata, or OCR layers * Encoded or obfuscated instructions (Base64, leetspeak, zero-width characters) evading detection \ Cross-context contamination where file content overrides system or developer instructions * Unauthorized tool invocation or workflow manipulation driven by file-based prompts * Leakage of sensitive data due to adversarial instructions embedded in files * Loss of explainability when behavior is influenced by unseen file content * Violations of transparency, auditability, and policy enforcement requirements **Attack Vector**: File upload > document ingestion / OCR / parsing pipeline \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None, especially in automated ingestion or agent workflows. \ **Confidentiality Impact**: High \ **Integrity Impact**: Critical \ **Availability Impact**: Medium **Framework** * OWASP-LLM: LLM01, LLM04, LLM05, LLM08 * OWASP-ASI: ASI-01, ASI-04, ASI-07, ASI-09, ASI-12 * EU AI Act: Articles 11, 12, 13, 50, plus Annex III robustness, safety, and risk-management requirements **References** \ \
### Data Security and Privacy
AI_DAT_SEC_001 Do not store secrets in code – Critical **Violation Summary**\ Storing secrets, such as API keys, access tokens, service credentials, MCP tokens, encryption keys, or database passwords, directly in code, configuration files, or agent prompt templates introduces an immediate and critical security vulnerability. Hard-coded secrets are easily exposed through source control, logs, error messages, LLM interactions, and dependency analysis. Once leaked, these credentials can be used to impersonate services, manipulate AI agent behavior, exfiltrate data, or compromise entire environments. **Affected Assets** * LLM * AI Agent * MCP Server **Technical Details**\ Storing secrets in code introduces several risks including: * Unauthorized access to internal systems, APIs, and third-party services * Full environment compromise if privileged keys (e.g., root tokens) are exposed * Impersonation of agents, MCP clients, or downstream services * Lateral movement enabled through leaked credentials * Leakage via LLM outputs, agent error messages, or repository scans * Irreversible compromise of production systems due to difficult secret rotation * Violations of governance, transparency, and credential-handling requirements **Attack Vector:** Source code / repository / agent configuration\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** Critical\ **Integrity Impact:** Critical\ **Availability Impact:** Medium **Framework** * **Nov 18, 2024 – OWASP-LLM**: LLM01, LLM03, LLM05, LLM08 * **March 2025 – OWASP-ASI**: ASI-01, ASI-04, ASI-09, ASI-12 * **Aug 1, 2024 – EU AI Act**: 1.11, 2.12, 3.13, 4.50 **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_DAT_SEC_009 If PII data must be shared, it must be encrypted - Critical **Violation Summary**\ Transmitting personally identifiable information (PII) without encryption exposes sensitive user data to interception, tampering, unauthorized access, and regulatory non-compliance. Unencrypted PII flowing between AI agents, MCP clients and servers, microservices, or external APIs can be harvested by attackers or internal adversaries through network sniffing, logging systems, or compromised intermediaries. Such exposure creates severe privacy, legal, operational, and reputational risks. **Affected Assets** * LLM * AI Agent * MCP Server **Technical Details**\ Transmitting unencrypted PII introduces several risks including: * Exposure of sensitive user information through network interception * Unauthorized access to identity data, enabling fraud or impersonation * Regulatory violations (GDPR, EU AI Act, state privacy laws) * Inability to ensure integrity or authenticity of transmitted data * Leakage through LLM logs, telemetry, or debugging outputs * Lateral movement or privilege escalation through harvested identity data * Failure to meet encryption, security, and risk-management obligations **Attack Vector:** Network transit / API calls / agent communication\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** Critical\ **Integrity Impact:** High\ **Availability Impact:** Low **Framework** * **Nov 18, 2024 – OWASP-LLM:** LLM03 (Data Leakage), LLM05 (Sensitive Information Disclosure), LLM08 (Insufficient Transparency & Auditability) * **March 2025 – OWASP-ASI:** ASI-01 (Input/Output Integrity), ASI-05 (Data Security & Handling), ASI-09 (Audit & Traceability), ASI-12 (Operational Monitoring) * **Aug 1, 2024 – EU AI Act:** Articles 1.11 (Technical Documentation), 2.12 (Record-Keeping), 3.13 (Transparency), 4.50 (General Transparency Obligations), plus GDPR-aligned data protection expectations reflected across the Act **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_DAT_SEC_010 Do not log PII – Critical **Violation Summary**\ Logging personally identifiable information (PII) exposes sensitive user data to unauthorized access, replication, and long-term retention in unsecured or low-visibility systems. Log files are frequently accessible to broader engineering, operations, analytics, or third-party tools and often persist indefinitely. Once PII enters logs, it becomes extremely difficult to control, delete, audit, or protect—creating severe privacy, compliance, and security risks across all AI and MCP-enabled environments. **Affected Assets** * LLM * AI Agent * MCP Server **Technical Details** Logging PII introduces several risks including: * Unauthorized internal access or external compromise of sensitive information * Accidental disclosure through debugging tools, telemetry pipelines, or log aggregators * Persistent exposure that violates data minimization and retention requirements * Inability to satisfy deletion, correction, or subject rights requests * Propagation of PII through downstream systems (LLM training data, observability tools, backups) * Legal and regulatory violations under GDPR, state privacy laws, and the EU AI Act * Loss of trust and reputational damage due to preventable data leakage **Attack Vector:** Logging systems / telemetry pipelines / observability tooling\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** Critical\ **Integrity Impact:** Medium\ **Availability Impact:** Low **Framework** * **Nov 18, 2024 - OWASP-LLM:** LLM03 (Data Leakage), LLM05 (Sensitive Information Disclosure), LLM08 (Insufficient Transparency & Auditability) * **March, 2025 - OWASP-ASI:** ASI-01 (Integrity), ASI-05 (Data Handling), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug, 1, 2024 - EU AI Act:** Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), GDPR-aligned data-minimization principles **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_DAT_SEC_011 Do not send PII to LLMs – Critical **Violation Summary**\ Sending personally identifiable information (PII) to an LLM exposes sensitive data to uncontrolled processing, persistence, training retention, unauthorized internal access, and unintended disclosure. LLMs are not guaranteed to handle PII according to data-minimization or privacy-by-design principles, and model outputs may inadvertently reveal, transform, or propagate sensitive information. This creates severe privacy, regulatory, and security risks across all AI-driven workflows. **Affected Assets** AI Agent **Technical Details**\ Sending PII to an LLM introduces several risks including: * Leakage of sensitive user information through outputs or indirect inference * Inclusion of PII in model logs, telemetry, or monitoring systems * Potential model retention or memorization of PII, enabling future extraction * Non-compliance with privacy regulations due to uncontrolled third-party processing * Exposure through prompt injection attacks that pull stored or inferred PII * Inability to enforce deletion, consent, or data subject rights * Violations of transparency, purpose limitation, and privacy-by-design obligations **Attack Vector:** LLM input channel\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** Critical\ **Integrity Impact:** Medium\ **Availability Impact:** Low **Framework** * **Nov 18, 2024 – OWASP-LLM:** LLM03 (Data Leakage), LLM05 (Sensitive Information Disclosure), LLM08 (Insufficient Transparency & Auditability) * **Mar 2025 – OWASP-ASI:** ASI-01 (Integrity), ASI-05 (Data Handling), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug 1, 2024 – EU AI Act:** Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), plus GDPR-aligned data-minimization and purpose-limitation requirements **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_DAT_SEC_012 Mask PII on user interfaces – Critical **Violation Summary**\ Displaying unmasked personally identifiable information (PII) on user interfaces exposes sensitive data to unauthorized viewing, shoulder surfing, screen sharing leaks, and over-privileged internal access. Any UI that renders full PII—names, addresses, SSNs, phone numbers, emails, financial data, or identifiers—creates a high risk of accidental disclosure and non-compliance. Unmasked PII can also be captured in screenshots, monitoring tools, session replay systems, or logs, further amplifying exposure. **Affected Assets** * LLM * AI Agent **Technical Details**\ Not masking PII on UI introduces several risks including: * Unauthorized access or accidental exposure of sensitive identity information * Violation of least-privilege and data-minimization principles * Increased likelihood of data leakage via screenshots, video recordings, demos, or shared sessions * Compromise through malicious insiders or overexposed customer support tools * Replication of PII into frontend logs, browser telemetry, or third-party analytics * Regulatory violations related to privacy, transparency, and secure data handling * Loss of user trust and potential legal liability **Attack Vector:** User interface display layer\ **Attack Complexity:** Low\ **Privileges Required:** None (visual exposure requires only observation)\ **User Interaction:** None\ **Confidentiality Impact:** Critical\ **Integrity Impact:** Low\ **Availability Impact:** Low **Framework** * **Nov 18, 2024 – OWASP-LLM:** LLM03 (Data Leakage), LLM05 (Sensitive Information Disclosure), LLM08 (Insufficient Transparency & Auditability) * **March 2025 – OWASP-ASI:** ASI-01 (Integrity), ASI-05 (Data Handling), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug 1, 2024 – EU AI Act:** Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), GDPR-aligned principles of data minimization and privacy-by-design **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_DAT_SEC_023 Redact PII from uploaded files - Critical **Violation Summary** \ If uploaded files (documents, PDFs, spreadsheets, images with OCR, logs, archives) are ingested without redacting personally identifiable information (PII), sensitive data can be unintentionally exposed, propagated, or retained across AI systems. Unredacted PII may be processed by LLMs, logged, cached, embedded in prompts, or transmitted to external services—creating severe privacy, regulatory, and security risks that are difficult to detect and remediate after ingestion. **Affected Assets** AI Agent **Technical Details** Failing to redact PII from uploaded files introduces several risks including: * Exposure of sensitive personal data through LLM processing, outputs, or logs * Propagation of PII into prompts, embeddings, vector stores, and downstream systems * Accidental disclosure via summaries, citations, or extracted insights * Inability to honor data minimization, retention limits, or subject rights requests * Increased blast radius when files are shared across agents or external tools * Elevated risk of data leakage through prompt injection or model inference * Violations of privacy-by-design, transparency, and record-keeping requirements **Attack Vector**: File upload → parsing / OCR / document ingestion pipeline \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None, especially in automated ingestion or agent workflows. \ **Confidentiality Impact**: Critical \ **Integrity Impact**: Medium \ **Availability Impact**: Low **Frameworks** * OWASP-LLM: LLM03, LLM05, LLM08 * OWASP-ASI: ASI-01, ASI-05, ASI-09, ASI-12 * EU AI Act: Articles 11, 12, 13, plus GDPR-aligned data-minimization and privacy-by-design principles embedded across the Act **References** \ \
AI_DAT_SEC_024 Uploaded files must not contain PII (Singapore) – Critical **Violation Summary**\ This applies to the information that is considered PII in Singapore. If files uploaded to an AI agent are ingested without redacting PII, sensitive data can be unintentionally exposed, propagated, retained, or disclosed through agent reasoning, LLM prompts, logs, embeddings, or downstream tool calls. Because AI agents often summarize, transform, store, and share file contents across systems, unredacted PII significantly amplifies privacy, compliance, and security risks and makes post-incident remediation extremely difficult. **Affected Assets** AI Agent **Technical Details** Failing to redact PII from files uploaded to AI agents introduces several risks including: * Exposure of sensitive personal data through agent outputs, summaries, or citations * Propagation of PII into prompts, vector databases, caches, logs, and telemetry * Uncontrolled sharing of PII with external LLM providers or third-party tools * Inability to comply with data minimization, retention limits, or deletion requests * Increased risk of data leakage via prompt injection or inference attacks * Broader blast radius when agents reuse or redistribute file content * Violations of privacy-by-design, transparency, and record-keeping requirements **Attack Vector**: File upload → agent ingestion / parsing \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None (especially in automated or agent-driven workflows) \ **Confidentiality Impact**: Critical \ **Integrity Impact**: Medium \ **Availability Impact**: Low **Frameworks** * OWASP LLM: LLM03, LLM05, LLM08 * OWASP ASI: ASI-01, ASI-05, ASI-09, ASI-12 * Singapore PDPA: Section 11, 13, 18, 24 **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_DAT_SEC_025 No file should contain any PII – Critical **Violation Summary**\ If files contain unredacted personally identifiable information (PII), there is risk of sensitive data access to unrestricted access, misuse, and downstream propagation. This increases the likelihood of data leakage, unauthorized scraping, AI training contamination, and regulatory violations. Once exposed, PII can be copied, indexed, cached, or redistributed beyond the organization’s control. **Technical Details** Failing to redact PII from publicly accessible files introduces several risks including: * Unrestricted access to sensitive personal data by internal users, contractors, or the public * Mass data harvesting, scraping, or indexing by automated tools and AI systems * Propagation of PII into LLM prompts, embeddings, search indexes, and external datasets * Inability to enforce consent, purpose limitation, or access controls * Permanent exposure due to caching, backups, screenshots, or mirrors * Increased insider threat and accidental disclosure risk * Severe regulatory, legal, and reputational impact **Attack Vector**: Public file access / shared repositories / collaboration platforms \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None \ **Confidentiality Impact**: Critical \ **Integrity Impact**: Medium \ **Availability Impact**: Low **Frameworks** * OWASP LLM: LLM03, LLM05, LLM08 * OWASP ASI: ASI-01, ASI-05, ASI-09, ASI-12 * EU AI Act: Article 11, Article 12, Article 13, Article 50, GDPR-aligned data minimization and privacy-by-design principles **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
### Identity and Access Control
AI_IAC_002 MCP client must authenticate MCP server – Critical **Violation Summary**\ If an MCP client does not authenticate the MCP server, it cannot verify the identity, legitimacy, or trustworthiness of the system providing tool responses, commands, or data. This creates an opportunity for attackers to impersonate the MCP server, intercept or modify traffic, inject malicious tool responses, or deliver falsified data that influences downstream agent reasoning. Without authentication, the MCP trust boundary collapses, enabling man-in-the-middle attacks, data manipulation, workflow corruption, and full compromise of AI-driven operations. **Affected Assets** * MCP Server * MCP Client * AI Agent **Technical Details**\ Not authenticating the MCP server introduces several risks including: * Server impersonation leading to injection of malicious or misleading responses * Man-in-the-middle interception and modification of MCP traffic * Unauthorized access to sensitive MCP capabilities, tools, and agent operations * Corruption of workflows through falsified output or manipulated data * Leakage of PII or sensitive context exchanged with the illegitimate server * Loss of integrity, trust, and accountability in MCP-driven decisions * Violations of transparency, security, and traceability requirements **Attack Vector:** Network/API communication between MCP client and server\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** High\ **Integrity Impact:** Critical\ **Availability Impact:** Medium **Framework** * **Nov 18, 2024 – OWASP-LLM:** LLM01 (Prompt/Instruction Injection), LLM04 (Model Behavior Manipulation), LLM05 (Sensitive Information Disclosure), LLM08 (Insufficient Transparency & Auditability) * **March 2025 – OWASP-ASI:** ASI-01 (Integrity), ASI-04 (Governance), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug 1, 2024 – EU AI Act:** Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), plus robustness and security obligations for high-risk systems **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_IAC_006 MCP server must authenticate all clients – Critical **Violation Summary**\ If an MCP server does not authenticate the client making requests, any unauthorized entity—including compromised agents, external attackers, or untrusted processes—can impersonate a legitimate client. This allows attackers to invoke privileged tools, access sensitive data, manipulate workflows, or trigger system actions without detection. Lack of client authentication effectively removes all trust boundaries, enabling full compromise of server-side capabilities and AI-driven operations. **Affected Assets** * LLM * AI Agent **Technical Details**\ Not authenticating the MCP client introduces several risks including: * Unauthorized invocation of high-privilege tools or system actions * Full impersonation of trusted agents, enabling malicious or deceptive requests * Data exposure through unrestricted access to server responses, APIs, or internal systems * Manipulation of downstream workflows via falsified or maliciously crafted requests * Escalation of privilege or lateral movement across connected systems * Loss of accountability, traceability, and auditability for all client-driven actions * Violations of integrity, transparency, and security obligations for regulated AI systems **Attack Vector:** Client → MCP server request path\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** High\ **Integrity Impact:** Critical\ **Availability Impact:** Medium **Framework (Compressed)** **Nov 18, 2024 – OWASP-LLM:** LLM01 (Instruction Injection), LLM04 (Behavior Manipulation), LLM05 (Sensitive Data Exposure), LLM08 (Transparency & Auditability Failures)\ **Mar 2025 – OWASP-ASI:** ASI-01 (Integrity), ASI-04 (Governance), ASI-09 (Traceability), ASI-12 (Monitoring)\ **Aug 1, 2024 – EU AI Act:** Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), plus Annex III robustness & security requirements **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_IAC_007 Inter-agent communication must be authenticated – Critical **Violation Summary**\ If agents communicate without authentication, any unauthorized party—including rogue agents, compromised services, or external attackers—can impersonate a legitimate agent and issue commands, request data, or alter system behavior. Non-authenticated inter-agent communication destroys trust boundaries between autonomous components and enables impersonation, privilege escalation, data leakage, workflow manipulation, and full compromise of multi-agent systems. Without identity guarantees, agent-to-agent messaging becomes a high-risk attack surface. **Affected Assets** AI Agent **Technical Details**\ Missing authentication between agents introduces several risks including: * Unauthorized agents impersonating trusted components to issue commands * Manipulation of agent workflows or decision chains through falsified messages * Leakage of sensitive data exchanged during inter-agent coordination * Injection of malicious instructions into distributed reasoning processes * Loss of accountability and inability to attribute harmful actions * Increased lateral movement risk across agent networks * Violations of integrity, trust, and regulatory controls for autonomous systems **Attack Vector:** Inter-agent message channel / network communication\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** High\ **Integrity Impact:** Critical\ **Availability Impact:** Medium **Framework** * **Nov 18, 2024 – OWASP-LLM:** LLM01 (Instruction Injection), LLM04 (Behavior Manipulation), LLM05 (Sensitive Data Disclosure), LLM08 (Transparency & Audit Failures) * **March 2025 – OWASP-ASI:** ASI-01 (Integrity), ASI-04 (Governance), ASI-07 (Reliability), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug 1, 2024 – EU AI Act:** Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), plus Annex III security & robustness expectations for high-risk systems **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_IAC_008 Agents must not hold excessive external system credentials – High/Critical **Violation Summary**\ When agents are configured with credentials to access more than three external systems, the blast radius of a compromise dramatically increases. Each additional credential expands the agent’s privilege footprint and creates new pathways for lateral movement, data exfiltration, unauthorized actions, and multi-system compromise. Over-privileged agents become single points of systemic failure if the agent is hijacked, attacked, misconfigured, or manipulated by an LLM prompt, all connected external systems are at risk simultaneously. **Affected Assets** AI Agent **Technical Details**\ Allowing an agent to hold multiple (3+) external system credentials introduces several risks including: * Large blast radius: compromising the agent compromises all connected systems * Increased likelihood of credential leakage through logs, LLM outputs, prompts, or tool interactions * Prompt injection enabling unauthorized use of high-privilege multi-system access * Lateral movement across different platforms (e.g., Jira → GitHub → AWS → Snowflake) * Violation of least-privilege and separation-of-duties principles * Difficulty revoking or rotating credentials in incident response * Loss of governance and traceability when many systems are accessed through one agent identity **Attack Vector:** Agent credential store / agent-initiated external API calls\ **Attack Complexity:** Low\ **Privileges Required:** None\ **User Interaction:** None\ **Confidentiality Impact:** Critical\ **Integrity Impact:** Critical\ **Availability Impact:** Medium to High **Framework** * **Nov 18, 2024 – OWASP-LLM:** LLM01 (Injection), LLM04 (Behavior Manipulation), LLM05 (Sensitive Data Disclosure), LLM08 (Transparency & Audit Failures) * **Mar 2025 – OWASP-ASI:** ASI-01 (Integrity), ASI-04 (Governance), ASI-05 (Safe Handling), ASI-09 (Traceability), ASI-12 (Monitoring) * **Aug 1, 2024 – EU AI Act:** Articles 11 (Documentation), 12 (Record-Keeping), 13 (Transparency), 50 (Transparency Obligations), Annex III controls emphasizing least privilege, system robustness, and secure integration **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com)\ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com)\
AI_IAC_009 LLM endpoints must require authentication – Critical **Violation Summary**\ If an LLM endpoint allows unauthenticated access, any external party can invoke the model without identity verification, usage controls, or accountability. This exposes the LLM to abuse, data leakage, prompt injection, denial-of-service, and unauthorized use of compute resources. In agentic and tool-enabled environments, unauthenticated access can also enable attackers to manipulate downstream workflows, trigger unsafe actions, or extract sensitive information without detection. **Affected Assets** LLM **Technical Details** Allowing unauthenticated access to an LLM endpoint introduces several risks including: * Unauthorized use of the model for malicious or abusive purposes * Prompt injection and adversarial inputs from unknown or untrusted actors * Leakage of sensitive context, system prompts, or embedded data * Abuse of compute resources leading to cost overruns or service degradation * Inability to enforce rate limits, quotas, or usage policies per identity * Loss of accountability, auditability, and forensic traceability * Circumvention of governance, approval, and access-control processes **Attack Vector**: Public or unauthenticated API endpoint \ **Attack Complexity**: Low \ **Privileges Required**: None \ **User Interaction**: None \ **Confidentiality Impact**: High \ **Integrity Impact**: High to Critical \ **Availability Impact**: High (due to abuse or denial-of-service) **Frameworks** Nov 18, 2024 – OWASP-LLM: LLM0, LLM03 LLM04, LLM08 \ Mar 2025 – OWASP-ASI: ASI-01, ASI-04, ASI-09, ASI-12 \ Aug 1, 2024 – EU AI Act: Articles 11, 12, 13, 50 and obligations for secure access control and robustness in high-risk and GPAI systems **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
### Vulnerability
AI_VULN_SEC_001 Do not allow dependencies with critical or high severity vulnerabilities – Critical **Violation Summary**\ Allowing AI agents to depend on libraries or packages with known critical or high-severity vulnerabilities introduces a direct and exploitable attack surface into the agent runtime. AI agents typically operate with elevated privileges, access sensitive data, invoke tools, and interact with external systems. Vulnerable dependencies can be exploited to execute arbitrary code, escalate privileges, leak secrets, poison agent behavior, or compromise downstream systems—often without direct interaction with the LLM itself. **Affected Assets** * AI Agent * MCP Server * LLM **Technical Details** Using dependencies with critical or high vulnerabilities introduces several risks including: * Remote code execution or arbitrary command execution within the agent environment * Credential theft, token leakage, or exposure of secrets used by the agent * Supply-chain attacks where malicious code is introduced via compromised packages * Manipulation or poisoning of agent logic, tool invocation, or decision flows * Lateral movement across systems accessed by the agent * Persistence mechanisms established through compromised libraries * Inability to trust agent outputs or actions due to compromised runtime integrity * Violations of secure development, patch management, and risk-management obligations **Attack Vector**: Vulnerable third-party dependency / supply-chain compromise \ **Attack Complexity**: Low \ **Privileges Required**: None (exploits often execute with agent privileges) \ **User Interaction**: None \ **Confidentiality Impact**: Critical \ **Integrity Impact**: Critical \ **Availability Impact**: Medium to High **Frameworks** * OWASP LLM: LLM05, LLM08 * OWASP ASI: ASI-05 * NIST SSDF: Practice RV.1 **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \
AI_VULN_SEC_002 Do not allow critical or high vulnerabilities in the code – Critical **Violation Summary**\ The presence of vulnerabilities in application or agent code introduces direct security risks that can be exploited to compromise confidentiality, integrity, and availability. Vulnerable code paths—such as injection flaws, insecure deserialization, broken authentication, improper authorization, or unsafe file handling—can be abused by attackers to execute arbitrary code, access sensitive data, manipulate AI behavior, or disrupt operations. In AI and agent-based systems, these vulnerabilities are especially dangerous because compromised code can influence autonomous decisions and propagate impact across multiple systems. **Affected Assets** * AI Agent * MCP Server * LLM **Technical Details** Having vulnerabilities in code introduces several risks including: * Remote code execution or command injection through exploitable code paths * Unauthorized access to sensitive data, credentials, or internal APIs * Manipulation of AI agent logic, reasoning flows, or tool invocation * Privilege escalation or bypass of authorization controls * Lateral movement across integrated systems and services * Persistence mechanisms established through exploited vulnerabilities * Loss of trust in application outputs and automated decisions * Violations of secure development lifecycle and regulatory requirements **Attack Vector**: Vulnerable application or agent code \ Attack Complexity: Low to Medium (depending on vulnerability type) \ Privileges Required: None (for many common vulnerabilities) \ User Interaction: None or minimal \ Confidentiality Impact: Critical \ Integrity Impact: Critical \ Availability Impact: Medium to High **Frameworks** * OWASP LLM: LLM05, LLM08 * OWASP ASI: ASI-05 * NIST SSDF: Practice RV.2 **References** [https://genai.owasp.org/llm-top-10/](https://genai.owasp.org/llm-top-10/?utm_source=chatgpt.com) \ [https://genai.owasp.org/initiatives/agentic-security-initiative/](https://genai.owasp.org/initiatives/agentic-security-initiative/?utm_source=chatgpt.com) \ ;
--- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.veedna.com/ai-kill-chain/the-stages-of-kill-chain/how-lineaje-policies-protect.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.