t2000-safeguards
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or safety bypasses were detected. The skill focuses on providing legitimate safety configuration and guardrails for autonomous agents.
- [EXTERNAL_DOWNLOADS]: The skill references and requires the installation of the
@t2000/clipackage from the npm registry, which is the expected tool for managing t2000 agent safeguards. - [COMMAND_EXECUTION]: The skill utilizes local shell commands via the
t2000binary to view and update agent safeguard configurations, such as transaction limits and the lock state.
Audit Metadata