gh-review-requests

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the GitHub CLI (gh) and uses uv to run a local Python script (fetch_review_requests.py). These operations are consistent with the skill's stated purpose of managing GitHub PRs and do not involve suspicious privilege escalation or persistence mechanisms.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (GitHub PR titles and author names).
  • Ingestion points: PR titles, author logins, and notification metadata fetched via gh api and the Python script in SKILL.md.
  • Boundary markers: The output is presented within a markdown table, providing a visual boundary for the agent.
  • Capability inventory: The skill has access to the Bash tool and can execute shell commands via uv and gh.
  • Sanitization: There is no explicit sanitization of PR titles before they are displayed in the markdown table. While a low-risk surface, an attacker could attempt to place instructions in a PR title to influence subsequent agent actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 08:15 AM
Security Audit — agent-trust-hub — gh-review-requests