phone

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

• Third-party content exposure detected (medium risk: 0.30). The skill monitors call transcripts (transcript array containing outsider-authored voice responses from the callee) when polling voice call status (blockrun_voice_status / GET /v1/voice/call/{call_id}).

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 0.70). The skill operates a direct financial workflow by making purchases and paid API requests (lookup, fraud checks, phone number buy/renew, and outbound voice calls) via automatic x402 wallet deductions against a local proxy endpoint (SKILL.md:43, 53, 69, 79, 115). No independent authentication or authorization mechanism (such as explicit user confirmation, prompt gating, or credentials required for each payment) is enforced by the service or execution layer for the payment route; payments are automatic via the x402 protocol from the wallet (SKILL.md:3, 27, 203).