Skills
skills/jawwadfirdousi/agent-skills/read-only-gh-pr-review/Gen Agent Trust Hub

read-only-gh-pr-review

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands and the GitHub CLI (gh) to perform repository analysis. This is documented as the primary purpose of the skill. To mitigate risk, the skill implements a multi-layered security wrapper in scripts/activate-gh-readonly.sh and scripts/gh-readonly.sh. This wrapper intercepts calls to the gh binary, shadows shell builtins like command and env to prevent bypasses, and enforces a strict allowlist of read-only subcommands (e.g., pr view, pr diff, api GET requests to specific endpoints). The skill also includes a test suite (scripts/test-readonly.sh) to verify these protections.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:00 AM