The Agent Skills Directory

[PROMPT_INJECTION]: The skill provides an interface for processing untrusted external data, creating a surface for indirect prompt injection.
Ingestion points: The agent ingests data from external blockchain logs and transactions via the Streams and Webhooks integrations documented in streams-reference.md and webhooks-reference.md.
Boundary markers: Example processing logic lacks explicit delimiters or instructions for the AI to ignore embedded commands within the blockchain data.
Capability inventory: The skill allows the agent to execute network requests, perform SQL queries via sql-explorer.md, and write to decentralized storage via ipfs-reference.md.
Sanitization: Integration examples do not demonstrate sanitization or validation of the ingested blockchain data before it influences subsequent agent actions.
[EXTERNAL_DOWNLOADS]: The skill interacts with external vendor infrastructure and official repositories.
Resources: Example code fetches configuration and data from api.quicknode.com, mpp.quicknode.com, and x402.quicknode.com.
Context: These resources are official endpoints for the Quicknode service. Automated scanner alerts regarding the IPFS gateway (quicknode-ipfs.com) are attributed to the shared nature of IPFS infrastructure and do not indicate malicious intent within the skill's code.

quicknode-skill