grill-with-docs

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary functions are interactive dialogue and local documentation management, which do not pose a security risk in this context.
  • [COMMAND_EXECUTION]: The skill enables the agent to read the codebase for context and write to specific documentation files (CONTEXT.md, CONTEXT-MAP.md, and ADRs). These actions are consistent with the skill's objective to 'update documentation inline as decisions crystallise' and are performed on files within the project's documentation structure.
  • [DATA_EXFILTRATION]: There are no network operations, external requests, or attempts to access sensitive system files or credentials.
  • [REMOTE_CODE_EXECUTION]: No patterns of remote script downloading, execution, or package installation were detected.
  • [PROMPT_INJECTION]: The instructions do not contain attempts to bypass AI safety guidelines or override system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 06:26 PM
Security Audit — agent-trust-hub — grill-with-docs