posting-review-summary
Warn
Audited by Snyk on Feb 16, 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 inspects PR metadata (title, description, test plan) in GitHub Actions and updates a sticky GitHub comment, meaning it ingests user-generated/untrusted content from a third-party GitHub PR as part of its workflow.
Audit Metadata