coval-eval-audit
Warn
Audited by Snyk on Sep 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 skill instructs the agent to read Coval evaluation runs, test sets, simulated conversations, and transcripts using CLI commands, which contain customer-generated test inputs and conversational content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata