creating-online-evaluations
Warn
Audited by Snyk on Nov 3, 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 skill instructs the agent to create and configure online evaluations that continuously score LLM generations and traces from production traffic, which originates from external users.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata