agentpay

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

• Third-party content exposure detected (medium risk: 0.30). The workflow consumes outsider-authored free text via AgentMail (https://x402.api.agentmail.to/v0/inboxes) in references/paid-services.md.

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

• Direct money access detected (medium risk: 0.30). The skill documents direct financial operations including buying, selling, swapping, bridging tokens, making payments (x402), placing bets on Polymarket, and sending funds via a CLI tool (polygon-agent) that interacts with an agent wallet. These direct financial operations are controlled by independent authentication and authorization mechanisms enforced by the service/execution layer (user sign-in, allowance limits, session keys, and explicit approval flows managed through the polygon-agent CLI and associated server infrastructure). Therefore, it qualifies for the medium tier.