Skills
skills/fandhe-ai/agent-reference-skills/implement-review-pr/Gen Agent Trust Hub

implement-review-pr

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands using the GitHub CLI (gh) to fetch pull request data and post reviews.
  • Evidence: Usage of gh pr view, gh pr diff, gh pr checks, and gh pr review in SKILL.md.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from GitHub pull requests.
  • Ingestion points: Pull request metadata and code diffs are retrieved using gh commands in SKILL.md (Step 1).
  • Boundary markers: Absent; there are no specific instructions or delimiters to prevent the agent from following instructions embedded within the PR content.
  • Capability inventory: The skill has the capability to post comments, approve pull requests, and request changes via gh pr review in SKILL.md (Step 7).
  • Sanitization: Absent; the skill does not implement any validation or sanitization of the pull request data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 12:06 PM
Security Audit — agent-trust-hub — implement-review-pr