gh-pr-metadata
Warn
Audited by Snyk on Mar 13, 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 directly reads the current GitHub PR title and body via
gh pr view(and uses the PR body/template from the repository) which are user-generated/untrusted GitHub content that the workflow explicitly reads and uses to validate and rewrite PR metadata, so malicious PR text could materially influence the agent's actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata