grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill is designed to manage internal project documentation and terminology. It reads existing project files and writes updates to glossaries (CONTEXT.md) and decision records (ADRs) as part of its primary functionality.
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it is instructed to explore the codebase and read documentation to answer design questions. However, the risk is minimal given that the skill's operations are confined to documentation management within the local environment and do not involve execution of untrusted code or exfiltration. Ingestion points: Project codebase files, CONTEXT.md, and ADRs. Boundary markers: Absent. Capability inventory: File read and write access for documentation maintenance. Sanitization: Absent.
Audit Metadata