pr-description
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs fetching and reading GitHub issues via "gh issue view --repo ... --comments" and repeatedly states "Always fetch the GitHub issue", so the agent ingests user-generated, untrusted issue/comments content that can shape its PR-writing behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata