zentao
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@leeguoo/zentao-mcpNode.js package from the NPM registry to provide thezentaocommand-line interface. This package is a vendor resource associated with the skill author. - [COMMAND_EXECUTION]: The skill leverages the
zentaoCLI to interact with ZenTao instances, performing operations such as record lookup, creation, and status updates. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill retrieves and displays data from ZenTao, including bug titles, task descriptions, story specifications, and user comments from the
SKILL.mdcontext. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers when handling data returned from the ZenTao instance.
- Capability inventory: The skill possesses the ability to execute various state-changing commands on the ZenTao instance, such as creating, resolving, or closing bugs and tasks.
- Sanitization: No explicit sanitization or content validation steps are documented for the data ingested from the external ZenTao platform.
Audit Metadata