llm-evals
Fail
Audited by Snyk on Nov 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate eval-building procedure, but it recommends installing a third-party package via an unpinned
npx skills@latest addcommand, which is mildly risky toward the user without any sign of malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow takes cases from production logs and bug reports (end-user and reporter free text) and feeds train traces containing that text to a fresh analyzer that proposes prompt or behavior changes, so an outsider's input can reach the agent without being selected first.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata