zentao-department
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the zentao-cli tool to interact with ZenTao. This is a legitimate use of a vendor-provided CLI for administrative tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes department data which could contain untrusted content. This is a common attack surface for data-fetching skills.
- Ingestion points: Results from zentao-cli department list and zentao-cli department get in SKILL.md and reference files.
- Boundary markers: None provided in the instructions.
- Capability inventory: CLI execution of zentao-cli.
- Sanitization: Not present in the analyzed files.
Audit Metadata