safe
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard documentation and code examples for using the official Safe{Core} SDK. All identified dependencies are well-known industry standards (e.g., @safe-global/protocol-kit, viem) and are fetched from official registries.
- [DATA_EXPOSURE]: The skill correctly instructs users to manage sensitive data such as private keys and RPC URLs using environment variables (
process.env), which is a security best practice for credential management. - [EXTERNAL_DOWNLOADS]: All external references and documentation links point to official and trusted domains associated with the Safe ecosystem, including safe.global, rhinestone.wtf, and pimlico.io. No suspicious or unverified download sources were identified.
- [COMMAND_EXECUTION]: Code examples use standard SDK methods for blockchain interactions. No dangerous shell commands, privilege escalation attempts, or persistence mechanisms were found.
- [INDIRECT_PROMPT_INJECTION]: While the skill enables the agent to process transaction data which could theoretically contain malicious instructions, the provided instructions do not include any patterns that increase this risk beyond the inherent properties of the blockchain domain. The focus is on implementing existing multisig security protocols.
Audit Metadata