skills/zhinkgit/embeddedskills/can/Gen Agent Trust Hub

can

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes system commands such as powershell, lsusb, and ip to identify and enumerate connected CAN interfaces and USB-CAN devices. These commands are executed with fixed arguments and no shell interpolation, which is a secure and necessary implementation for hardware discovery in this context.
  • [SAFE]: The skill ingests external data from the CAN bus and database files (e.g., DBC, ARXML) for decoding purposes. This data is handled through standard parsing libraries such as python-can and cantools, and there is no evidence of unsafe dynamic execution or data exfiltration. The use of local state and configuration files follows established practices for local tool configuration management.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 07:57 AM