grill-me-with-docs
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes content from the repository, including CONTEXT.md, CONTEXT-MAP.md, and ADR files, to guide user interactions and perform documentation updates. This creates a potential surface for indirect prompt injection if those files were to contain malicious instructions.
- Ingestion points: The agent explores the codebase and reads documentation files (CONTEXT.md, CONTEXT-MAP.md, and files in docs/adr/) at runtime.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the processed documentation or source code.
- Capability inventory: The skill is capable of modifying files (updating CONTEXT.md and creating ADRs) and interacting with the user via the AskUserQuestion tool.
- Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is interpolated into the agent's logic or documentation writes.
Audit Metadata