agent-wallet-policy
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
circleCLI to interact with wallet policies, such as viewing limits and preparing commands for the user to set new limits. - [EXTERNAL_DOWNLOADS]: The skill references documentation and source code from Circle's official domains and GitHub repository (
agents.circle.com,developers.circle.com,github.com/circlefin). These are recognized as well-known and trusted services. - [INDIRECT_PROMPT_INJECTION]: The skill processes structured JSON output from the
circleCLI (circle wallet limit --output json). This introduces a minor surface where the agent's behavior could be influenced by the data returned from the tool, though the risk is mitigated by the specific context of wallet policy management.
Audit Metadata