gh-create-pr
Warn
Audited by Snyk on Apr 7, 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 runs gh pr view to read existing PR number/title/body and instructs the agent to "enhance" or edit existing PR descriptions (see "Existing PR for branch: gh pr view --json number,title,body" and "If a PR already has a meaningful description, enhance it rather than replace it entirely"), so it ingests untrusted, user-generated GitHub PR content that can influence subsequent PR-editing actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata