smoke-test
Warn
Audited by Snyk on Apr 18, 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's Step 1 explicitly instructs fetching PR details (title, description, changed files, comments) — i.e., reading public pull request content (user-generated third‑party data) that the agent must interpret to determine tests, which can materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata