fix-pr-comments

Warn

Audited by Snyk on Feb 17, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and consumes user-generated PR review and inline comments from GitHub (via "gh pr review list" and "gh api repos/{owner}/{repo}/pulls/{number}/comments"), which are untrusted third-party content the agent is expected to read and act on.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill invokes the GitHub API endpoint (gh api repos/{owner}/{repo}/pulls/{number}/comments) at runtime to fetch PR review comments, and those fetched comments are used as direct instructions that control the agent's edits, making this external content a required runtime dependency and thus risky.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:48 AM