fund-agent-wallet
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill limits tool execution to the
circleCLI via a restrictiveallowed-toolswhitelist. No generic shell access or dangerous commands were identified. - [SAFE]: No hardcoded credentials, sensitive file access (e.g.,
.ssh,.env,.aws), or unauthorized data exfiltration patterns were detected. - [SAFE]: The instructions include explicit security guardrails for the agent, such as requirements to never store private keys and to always verify transaction details with the user.
- [SAFE]: External links point to official documentation and configuration files on trusted vendor domains (
circle.com). - [SAFE]: The skill does not ingest untrusted external data (e.g., web scraping or arbitrary file reading) for command interpolation, minimizing the surface for indirect prompt injection.
Audit Metadata