viem-integration
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates code based on user-provided inputs such as Ethereum addresses and RPC URLs. It effectively mitigates potential injection risks by providing specific validation rules, including regex requirements for addresses and strict protocol enforcement for RPC endpoints.
- [CREDENTIALS_UNSAFE]: The skill addresses secret management by explicitly instructing the agent never to hardcode private keys, instead requiring the use of environment variables with runtime validation.
- [EXTERNAL_DOWNLOADS]: The skill references standard, well-known Node.js packages (viem, wagmi) and official documentation sources (viem.sh, wagmi.sh) which are consistent with the skill's stated purpose.
Audit Metadata