grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from the user's codebase, including documentation and source code, which serves as a potential vector for indirect prompt injection.
- Ingestion points: The agent reads files such as
CONTEXT.md,CONTEXT-MAP.md, and Architectural Decision Records (ADRs) within thedocs/adr/directory. - Boundary markers: The instructions do not define delimiters (like XML tags) to isolate file content from the system instructions.
- Capability inventory: The skill requires read access to the codebase and write access to create or update
CONTEXT.mdand ADR files. - Sanitization: No explicit logic or instructions are provided to sanitize or validate the content retrieved from external files before it is processed by the agent.
Audit Metadata