grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests and processes data from the repository codebase to inform its grilling sessions and document updates.
- Ingestion points: Reads local source files, CONTEXT-MAP.md, CONTEXT.md, and Architecture Decision Records (ADRs) to cross-reference with user-provided information.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' directives when the agent processes content read from the codebase.
- Capability inventory: The skill is capable of modifying documentation files (CONTEXT.md and ADRs) and interacting with the user through the AskUserQuestion tool.
- Sanitization: No explicit sanitization or validation of the ingested repository content is performed before it is integrated into the agent's reasoning process.
Audit Metadata