skeptic
Warn
Audited by Snyk on Jul 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Required workflow ingests a “Hunter findings file” (free-form text fields like claim/evidence/runtime trigger) that is authored by an outsider (the Hunter), and this text is read and then used to generate the LLM’s JSON output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata