grill-with-docs
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No patterns of instruction override or safety bypass were detected. The skill uses structured XML-like tags to define its operational boundaries.
- [DATA_EXFILTRATION]: The skill does not use network tools or external APIs. Its operations are restricted to reading and writing documentation files within the local repository.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unverified dependencies are present. The skill exclusively manages Markdown documentation.
- [COMMAND_EXECUTION]: The skill performs codebase exploration to verify domain logic but does not execute arbitrary shell commands or high-privilege operations.
- [SAFE]: The skill implements structured documentation patterns (ADRs and Context Maps) and includes logic for localized context awareness in multi-context repositories.
Audit Metadata