The Agent Skills Directory

[PROMPT_INJECTION]: No malicious instructions or attempts to bypass agent safety guidelines were detected. The instructions are purely descriptive and instructional.- [CREDENTIALS_UNSAFE]: The skill mentions private keys and mnemonics, but only as placeholders (e.g., "0x...", "legal winner thank year...") within documentation examples. No actual sensitive credentials or secrets are hardcoded.- [DATA_EXFILTRATION]: No unauthorized network operations or access to sensitive local files were found. Network references are limited to well-known Ethereum RPC providers and documentation sources.- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote script execution or download untrusted code. It references the official viem library modules.- [COMMAND_EXECUTION]: No shell commands, subprocess spawning, or system-level executions are present in the skill content.- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for blockchain interactions (reading/writing contracts), which is its primary purpose. It does not ingest untrusted data in a way that would trigger unintended agent behavior beyond its defined scope.

viem