braintrust-red-team-agent
Warn
Audited by Snyk on Aug 20, 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’s required runtime workflow is “red team adversarial testing against a stated threat model/policy boundary,” which necessarily ingests adversarial free-text artifacts (e.g., generated or user-supplied attack payloads/trace content) to evaluate for existence-of-violation claims.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata