plan-privacy-compliance
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze existing codebases and documentation to identify personal data flows. While processing untrusted data could theoretically introduce indirect prompt injection, the risk is minimal given the scope of the skill's operations.\n- Ingestion points: Processes application source code and privacy policy text provided by the user.\n- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided for the analysis phase.\n- Capability inventory: The skill is limited to generating a markdown plan (
plan-privacy-compliance.md) and lacks capabilities for network operations, privilege escalation, or direct code execution.\n- Sanitization: No explicit sanitization or filtering logic is defined for the content being analyzed.\n- [SAFE]: No malicious patterns, obfuscation, remote code execution, or persistence mechanisms were detected. The skill's purpose as a documentation and planning assistant is consistent with its behavior.
Audit Metadata