wuji-cli-doctor
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
wujicommand-line utility to perform hardware health checks. This is the primary and intended functionality of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill involves the agent processing structured JSON output from the diagnostic utility. While this is a data ingestion surface, the risk is negligible as it originates from a local vendor-provided binary.
- Ingestion points: Diagnostic report output from the
wuji doctor --jsoncommand. - Boundary markers: None defined.
- Capability inventory: Local execution of specific diagnostic commands via the
wujibinary. - Sanitization: No specific input or output sanitization is described in the documentation.
Audit Metadata