grill-me-with-docs
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to explore the codebase to answer questions and validate documentation accuracy. This translates to standard read operations (e.g., ls, cat, or grep) within the user's project directory to facilitate the documentation alignment process.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from project documentation and source code files, which could potentially contain malicious instructions intended to manipulate the agent's behavior during the interview session. * Ingestion points: Reads data from LANGUAGE.md, MAP.md, CONTEXT-MAP.md, and the codebase directory. * Boundary markers: No delimiters or warnings are used to distinguish project content from system instructions. * Capability inventory: The agent has file-reading and documentation-writing capabilities, as well as the ability to conduct interactive sessions with the user. * Sanitization: The skill does not implement any validation or sanitization of the content it reads from the local filesystem.
Audit Metadata