agentic-gateway

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs agents to call Alchemy NFT and Portfolio APIs (e.g., references/data-nft-api.md and references/data-portfolio-apis.md) and to request metadata/tokenUri resolution (IPFS/external URLs and raw.metadata fields), which are user-generated/untrusted third-party contents the agent is expected to read and that could materially influence subsequent actions.

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

• Direct money access detected (high risk: 1.00). The skill explicitly exposes payment and wallet capabilities: it documents x402 and MPP payment protocols (USDC on-chain via x402/EIP-3009 and Tempo, and Stripe card payments via MPP), requires creating/issuing payments (e.g., "npx @alchemy/x402 pay", "create credential with mppx", retry with Payment/Payment-Signature/Authorization headers), and includes wallet setup/funding and signing (SIWE/SIWS, wallet management, transactions). These are specific, concrete mechanisms to move funds and sign transactions (crypto/payments and Stripe integration), not generic tooling. Therefore it grants direct financial execution authority.