ae-evaluation
Warn
Audited by Snyk on Oct 23, 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 workflow allows importing datasets and AI Monitor traces containing untrusted outsider-submitted data into evaluation cases, which are subsequently read and processed by the LLM agent during evaluation runs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata