zentao-ticket
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs and executes shell commands using the
zentao-clibinary. It incorporates user-provided inputs, such as ticket titles and descriptions, directly into command arguments (e.g.,zentao-cli ticket create --title <title>). This pattern presents a potential command injection surface if the inputs are not properly sanitized or escaped. - [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it retrieves and processes content from an external source (the ZenTao ticket system).
- Ingestion points: Untrusted data enters the agent context via
zentao-cli ticket listandzentao-cli ticket get(specifically the title and description fields). - Boundary markers: The skill does not define specific delimiters or instructions to help the agent distinguish between its core instructions and the data retrieved from tickets.
- Capability inventory: The skill possesses capabilities to read, create, update, and delete data using shell commands.
- Sanitization: There is no visible mechanism in the provided files for sanitizing or validating ticket content before it is processed by the AI agent.
Audit Metadata