review-pr

Warn

Audited by Snyk on Apr 3, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches PR review bodies and inline comments from GitHub via gh api (e.g., "gh api repos/PrefectHQ/fastmcp/pulls/{PR_NUMBER}/comments") and instructs the agent to evaluate and act on those bot/user-generated review comments, so untrusted third‑party content from PR comments can directly influence fixes, replies, and subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 3, 2026, 08:50 PM
Issues
1