zentao-program
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
zentao-clibinary to perform ZenTao program management tasks. This execution is scoped to the skill's primary purpose and is explicitly declared in the metadata as a requirement. - [INDIRECT_PROMPT_INJECTION]: The skill handles user-provided data and external program information, creating a standard surface for potential indirect prompt injection. However, this is inherent to the tool's management functionality.
- Ingestion points: Command arguments such as
--name,--code, and--descinreferences/zentao-program-create.mdandreferences/zentao-program-update.md, as well as API output processed by the agent. - Boundary markers: None explicitly defined in the provided instruction files.
- Capability inventory: Shell execution limited to
zentao-clicommands for program CRUD operations. - Sanitization: No explicit sanitization or escaping instructions are provided within the skill files.
Audit Metadata