github-review

Warn

Audited by Snyk on Feb 28, 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 requires running ghx/collect (see SKILL.md and references/SCRIPTS.md and scripts/collect.sh) to fetch PR artifacts such as pr.diff, files.json, review_threads.json, and comments.json from GitHub (public/user-generated content) which the agent is expected to read and use to generate reviews, so untrusted third‑party content can directly influence its decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 11:50 AM