grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the local repository (source code and existing documentation) to inform its responses and documentation updates. This creates a surface for indirect prompt injection if project files contain malicious instructions.
- Ingestion points: The skill reads files from the
src/directory,CONTEXT.md,docs/adr/, andCONTEXT-MAP.mdas specified inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to differentiate between user instructions and data processed from the codebase.
- Capability inventory: The skill's capabilities are restricted to file system operations (reading codebase and writing documentation). It does not have network access or shell execution capabilities.
- Sanitization: No specific sanitization or filtering of codebase content is mentioned before it is processed by the model or written into documentation.
Audit Metadata