create-pull-request
Warn
Audited by Snyk on Mar 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to read and summarise repository commit messages (git --no-pager log --oneline origin/HEAD..HEAD) and to query GitHub PR/repo data (gh pr view, gh repo view and a GitHub PR template URL), which are user-generated/untrusted contents from public GitHub and are used to populate PR titles/bodies and decide PR behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata