The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the zentao CLI to interact with the ZenTao PMS. It executes commands to query, create, and update business objects such as tasks, bugs, and requirements. These operations are performed within the context of the user's authenticated environment and are limited to the intended functionality of the platform.
[EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the vendor's official command-line interface using npm install -g zentao-cli. This is a standard deployment method for the tool required by the skill.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and display data from the ZenTao server (e.g., bug descriptions, requirement specifications). The instructions provide clear context for interpreting this data as business information rather than instructions, which mitigates the risk of the agent accidentally executing commands embedded in the data.
[DATA_EXPOSURE]: The skill interacts with local configuration files (~/.config/zentao/zentao.json) and environment variables containing authentication tokens. However, it contains explicit and repeated instructions to the AI to never request, display, or store user passwords or tokens in chat logs or repository files, adhering to high security standards for credential handling.

zentao-tour