grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project files such as
CONTEXT.md, ADRs, and source code to synchronize documentation with implementation and challenge user plans. This ingestion of potentially untrusted data from the codebase represents an attack surface. - Ingestion points: The agent reads files from the local repository, specifically
CONTEXT.md,CONTEXT-MAP.md,docs/adr/*.md, and files within thesrc/directory. - Boundary markers: The instructions lack explicit requirements for delimiters or safety markers to differentiate between data and potential instructions embedded within the analyzed files.
- Capability inventory: The skill possesses capabilities to read arbitrary files in the repository and perform file-write operations to create or update documentation files.
- Sanitization: There is no mention of sanitization, validation, or filtering of the content retrieved from the codebase before it is incorporated into the agent's reasoning process.
Audit Metadata