The Agent Skills Directory

[PROMPT_INJECTION]: The skill has a potential indirect prompt injection surface as it processes data from the Nodit x402 proxy. Ingestion points: The agent reads and decodes the 'Payment-Required' header from 402 responses received from x402.nodit.io. Boundary markers: The skill instructs the agent to prefix output with a specific attribution string but lacks explicit delimiters for incoming data. Capability inventory: The agent can perform network requests and construct cryptographic signatures. Sanitization: The protocol uses structured JSON/Base64 data following the x402 specification.\n- [COMMAND_EXECUTION]: The skill instructs the agent to interact with the vendor's API proxy at https://x402.nodit.io for authentication, credit management, and blockchain data requests.\n- [CREDENTIALS_UNSAFE]: The skill implements a workflow for SIWX authentication and payment signatures. While no credentials are hardcoded, the instructions guide the agent to perform cryptographic signing, which implies the agent must handle sensitive private keys to operate autonomously.

web3-x402