create-pr
Warn
Audited by Snyk on Aug 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In
SKILL.mdStep 1/“Gather Info”, the workflow reads outsider-influenced free text from Git commit messages viagit log/git diffover remote refs (refs/remotes/origin/...), which is used to generate the PR title/body and then scanned/sanitized at Steps 3-4/4b.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata