skills/polya20/grill-me/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes the GitHub CLI (gh) to create issues, which is its primary intended functionality and aligns with the principle of least privilege for its stated purpose.
  • [SAFE]: The instructions implement data minimization and protect internal codebase information by mandating that generated issues describe user-facing behaviors instead of internal code, specifically forbidding file paths and line numbers.
  • [SAFE]: The skill manages an indirect prompt injection surface where user-provided bug descriptions are used to populate issues. The risk is effectively mitigated through structured templates and instructions to avoid technical details. 1. Ingestion points: user bug reports and descriptions. 2. Boundary markers: issue body templates. 3. Capability inventory: gh issue create (write) and Explore subagent (read). 4. Sanitization: enforcement of domain language and exclusion of internal implementation specifics.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:36 AM
Security Audit — agent-trust-hub — qa