triage-nda
Warn
Audited by Snyk on Mar 13, 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 accepts and ingests third-party NDA content via "File upload / URL / Pasted text" (Step 1) and requires the agent to read and triage that content as part of its workflow (Step 3), so untrusted external documents could materially influence decisions and enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata