find-a-great-movie
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from an external source (goodrecmovies.com), creating a surface for potential prompt injection via untrusted content.
- Ingestion points: The skill fetches content from
https://goodrecmovies.com/index.md,https://goodrecmovies.com/series.md, and interacts with a tool athttps://goodrecmovies.com/mcp. - Boundary markers: The instructions do not provide explicit delimiters (e.g., XML tags or backticks) or warnings for the agent to treat the fetched movie rankings as untrusted text.
- Capability inventory: The skill's capabilities are limited to network requests (GET/POST) and data presentation. It does not have access to file-writing, system commands, or sensitive environment variables.
- Sanitization: There are no instructions for the agent to sanitize the incoming movie titles or descriptions before presenting them to the user.
Audit Metadata