experiment-design
Warn
Audited by Snyk on Aug 24, 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
experiment-design→ Survey mode “Entry Point A: QSF Parsing”, the workflow explicitly parses a user-supplied Qualtrics.qsfJSON file (including survey question/response text such as free-text items) into the LLM’s runtime context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata