The Agent Skills Directory

[SAFE]: The skill serves as a reference guide for the Wagmi Ethereum library and does not contain any executable scripts, obfuscated code, or malicious instructions.
[EXTERNAL_DOWNLOADS]: The documentation references the create-wagmi CLI for project scaffolding (e.g., npm create wagmi). This is a standard and well-known tool for bootstrapping blockchain projects using the official library.
[INDIRECT_PROMPT_INJECTION]: The skill describes methods for the agent to ingest data from the Ethereum blockchain (e.g., reading contract states, resolving ENS names). While this introduces a surface for indirect prompt injection via untrusted chain data, it is the intended purpose of the library.
Ingestion points: Blockchain data retrieved via useReadContract, useEnsName, and useBalance hooks (defined in references/react-read-write-contract.md and references/react-ens.md).
Boundary markers: No specific boundary markers or 'ignore' instructions are provided in the documentation snippets.
Capability inventory: The skill provides the agent with patterns to perform contract writes, send transactions, and sign messages (useWriteContract, useSendTransaction, useSignMessage).
Sanitization: The library uses standard Viem-based decoding, but no specific LLM-level sanitization for ingested data is discussed.

wagmi