prior-auth-review-skill
Warn
Audited by Snyk on Jul 30, 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). In Subskill 1 (“Intake & Assessment”), the workflow ingests outsider-provided clinical documentation via “Paste clinical notes, upload file, or provide summary” and then performs medical-necessity extraction from that text during runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata