cross-eval
Warn
Audited by Snyk on Aug 21, 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
/cs:cross-eval <memo-or-brief>workflow explicitly ingests an outsider-provided free-text “memo / brief” supplied directly by the user as the argument to the command and then sends that memo to multiple model providers for review.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata