changelog-gen
Warn
Audited by Snyk on Mar 1, 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 reads git history and sends commit messages to the model ("Runs git log... and sends them to GPT-4o-mini" in SKILL.md), which ingests untrusted user-generated commit content that could contain instructions influencing model behavior.
Audit Metadata