grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to facilitate architectural design reviews and maintain domain documentation. It operates on local project files such as CONTEXT.md and ADRs.\n- [COMMAND_EXECUTION]: While the skill permits the use of the Bash tool, its instructions focus on codebase exploration and terminology validation rather than executing external or harmful scripts.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes project documentation and code which could theoretically contain malicious instructions.\n
  • Ingestion points: Reads CONTEXT.md, docs/adr/, and source files.\n
  • Boundary markers: Not explicitly defined in the instructions.\n
  • Capability inventory: Uses Bash, Write, and Edit tools to interact with the filesystem.\n
  • Sanitization: Content is processed for terminology alignment without specific sanitization filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 01:51 PM
Security Audit — agent-trust-hub — grill-with-docs