privacy-policy
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to research product websites to map data collection practices. This ingestion of untrusted external content introduces a risk where malicious actors could embed hidden instructions on those websites to manipulate the agent's output or logic.
- Ingestion points: The 'Workflow' section in SKILL.md instructs the agent to 'Visit the product website' to identify data collection methods and features.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the fetched website content as data only and to ignore any embedded directives.
- Capability inventory: The agent is authorized to read external content and process it into structured legal deliverables.
- Sanitization: The skill does not define any mechanisms for sanitizing or validating the information retrieved from external URLs before it is processed.
Audit Metadata