mdapi-conversion

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill transforms arbitrary external webpages and user-submitted files into Markdown via mdapi.io, ingesting outsider-authored free text through the input parameter without prior selection.

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

• Direct money access detected (medium risk: 0.30). The skill documents operational payment and token activation workflows via x402 (autonomous payment via PAYMENT-SIGNATURE/PAYMENT-REQUIRED headers and manual cryptocurrency transfers verified on-chain via token/memo headers), representing direct financial operations (transfers/charges/settlement authorization). The direct payment and token activation routes rely on service-enforced cryptographic validation (on-chain verification of transactions and memos, server-side authentication of Bearer tokens and activation signatures), constituting qualifying independent access control.