wuji-cli-doctor-manual
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'wuji' command-line interface to perform hardware diagnostics. These commands are documented for listing recipes and executing thumb-opposition tests on robotic hardware.
- [DATA_EXPOSURE]: The skill accesses 'joint_states' and 'joint_diagnostics' from a connected robotic device. This is telemetry data specific to the hardware's operation and does not involve accessing sensitive user files, credentials, or environment variables.
- [REMOTE_CODE_EXECUTION]: No patterns for downloading or executing remote scripts (such as curl-to-bash) were detected. All execution is limited to the local 'wuji' binary which is a prerequisite for the skill.
- [OBFUSCATION]: The skill uses clear, plain-text instructions. No hidden characters, encoded strings, or homoglyph attacks were identified.
Audit Metadata