grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for project documentation management and structured interviewing. It operates on local text files and does not exhibit unauthorized network activity or credential harvesting.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by processing repository file content. 1. Ingestion points: The skill reads CONTEXT.md, CONTEXT-MAP.md, and files in docs/adr/ (SKILL.md). 2. Boundary markers: No specific instructions or delimiters separate user-provided file content from the agent's logic. 3. Capability inventory: The skill can write to the filesystem and call the dex planning skill (SKILL.md). 4. Sanitization: No sanitization is implemented for the documentation content.
  • [EXTERNAL_DOWNLOADS]: The skill references a 'dex' skill. This is an internal capability reference and not an untrusted external download.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:55 PM
Security Audit — agent-trust-hub — grill-with-docs