smart-intake
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required workflow reads and extracts the contents of user-provided folder documents (e.g., bank statements/PDF/CSV and other files) into the agent’s context for extraction/normalization, which can include outsider-authored free text from third parties embedded in those documents.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata