trustlayer-sybil-scanner

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). Yes — the skill explicitly fetches and parses user-generated review data and anomaly flags from the public TrustLayer API (e.g., https://api.thetrustlayer.xyz/trust/: and related agent/reviewer endpoints and public agent pages), and uses those untrusted third‑party contents to drive blocking/warning decisions that affect subsequent actions.