fraudlabs-pro
Warn
Audited by Snyk on Mar 11, 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 shows the agent calling the external FraudLabs Pro API via Membrane (e.g., "Screening" actions like Get Transaction/Get Order and the "Proxy requests" section), which ingests third‑party/user‑generated transaction/customer data that the agent is expected to read and which could materially influence decisions, so it exposes the agent to untrusted third‑party content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata