look-up-a-title
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source (goodrecmovies.com), creating a surface for indirect instructions to potentially influence the agent.
- Ingestion points: Data is fetched via Markdown URLs (e.g., https://goodrecmovies.com/movie/tt0111161.md) and an MCP tool.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are provided to delimit the external content.
- Capability inventory: The skill is restricted to reading movie data and providing information to the user; no high-risk capabilities such as file writing, shell access, or credential management were identified.
- Sanitization: There is no evidence of sanitization or filtering of the fetched Markdown content.
Audit Metadata