grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with the local codebase and user inputs, creating a surface for indirect prompt injection.\n- Ingestion points: The agent reads the contents of
CONTEXT.md,CONTEXT-MAP.md, Architectural Decision Records (ADRs), and source code files within the repository.\n- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading these files.\n- Capability inventory: The skill allows the agent to read and write files to manage project documentation. It does not possess network access, arbitrary command execution, or privilege escalation capabilities.\n- Sanitization: There is no evidence of sanitization or validation of the content read from the files before it is processed by the agent.
Audit Metadata