changelog
Warn
Audited by Snyk on Jun 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: 0.75). The skill’s runtime workflow uses
git logto read commit messages from the repository (i.e., text authored by other contributors/outsiders), which the agent then parses and injects into the LLM context to generate/updateCHANGELOG.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata