skills/ismail9k/skills/review-prs/Gen Agent Trust Hub

review-prs

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub pull request descriptions, comments, and external issue trackers to inform its code review process. Malicious content within these fields could theoretically influence the review findings.
  • Ingestion points: Data is gathered via gh pr list, gh pr view, and gh api calls for comments, as well as reading linked issues from trackers.
  • Boundary markers: The instructions do not specify explicit delimiters or "ignore" instructions when passing this external data to the sub-agent for analysis.
  • Capability inventory: The skill can execute git and gh commands, and has the ability to post review comments to GitHub via the API.
  • Sanitization: The skill includes a 'Check every finding' step and requires user confirmation of the target PR list, providing a layer of oversight before actions are taken.
  • [COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) to perform repository operations, such as viewing repositories, listing pull requests, and fetching code history. These are standard operations for the described workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 01:56 PM
Security Audit — agent-trust-hub — review-prs