maiat-token-safety

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches token analysis from the public Maiat API endpoints (e.g., https://app.maiat.io/api/v1/token/<contract_address> and the x402 endpoints) and instructs the agent to read those responses (verdict, riskFlags, riskSummary) to decide whether to proceed with swaps, so untrusted third-party content can materially influence agent actions.