privacy-policy-audit
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (privacy policy documents via paths, URLs, or text) which creates a surface for indirect prompt injection.
- Ingestion points: External privacy policies provided as URLs, file paths, or pasted text in the 'Create' and 'Update' modes.
- Boundary markers: The instructions do not specify the use of strict delimiters (e.g., XML tags) to isolate the untrusted content from the agent's core instructions.
- Capability inventory: The skill utilizes delegation patterns to spawn specialized consultation agents (e.g., General Counsel, Compliance Officer) based on findings derived from the content of the analyzed document.
- Sanitization: There are no explicit instructions for sanitizing or filtering instructions that might be embedded within the processed privacy policies to prevent accidental obedience.
Audit Metadata