release-skills
Warn
Audited by Snyk on Mar 2, 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). This skill explicitly ingests untrusted, user-generated GitHub data (e.g., uses git log and gh pr view as shown in Step 2 and Step 4 to read commit messages, PR bodies/authors and looks for "BREAKING CHANGE") and relies on that content to decide version bumps and changelog/attribution, so third-party content can materially change behavior.
Audit Metadata