grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a documentation and design review assistant. Its activities are confined to interviewing the user and managing local files like
CONTEXT.mdand ADRs. No unauthorized network activity, credential harvesting, or suspicious instructions were detected.- [DATA_EXPOSURE]: The instructions enable the agent to explore the codebase to answer questions and verify documentation consistency. This access is standard for development tools and is used exclusively for domain awareness within the local workspace.- [INDIRECT_PROMPT_INJECTION]: The skill reads external data from the codebase and project documentation. While this creates a surface for indirect prompt injection, the skill's capabilities are limited to documentation management, and no unsafe interpolation or exfiltration patterns are present.
Audit Metadata