flare-fdc
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs using Web2Json to fetch arbitrary public Web2 URLs and to POST to verifier and DA Layer endpoints to retrieve externally provided attestation responses/proofs (see "External data handling", "Web2Json Quick Reference", and the workflow steps), meaning the agent/dev flow consumes untrusted third‑party content that can materially influence verification and downstream actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata