refine-agent-work
Warn
Audited by Snyk on Sep 3, 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 reviews agent-created work surfaces like branches, pull requests, and commits, which can contain outsider-authored text and code modifications processed at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata