code-pull-request
Warn
Audited by Snyk on Aug 1, 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). The skill reads outsider-authored PR/MR comment bodies at runtime via the CLI commands in references/read-comments.md (e.g.,
gh pr view ... --json comments/glab mr note list), and then presents that free text to the human as part of the workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata