The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @ant-design/cli package globally using npm to provide its core functionality. This is a vendor-owned resource.
[COMMAND_EXECUTION]: The skill frequently executes shell commands via the antd CLI tool to query component data, lint source files, and analyze project structures.
[DATA_EXFILTRATION]: The antd bug and antd bug-cli commands utilize a --submit flag to send data to external bug-tracking systems. To mitigate unauthorized data transfer, the skill requires the agent to preview the report and obtain explicit user confirmation before submission.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and acting upon data from potentially untrusted sources.
Ingestion points: Data enters the agent's context through the output of commands such as antd info, antd demo, antd doc, antd usage, and antd lint (SKILL.md).
Boundary markers: No specific delimiters or safety instructions are used to separate ingested data from agent instructions.
Capability inventory: The skill possesses shell execution capabilities for the antd CLI and network access via bug reporting flags.
Sanitization: There is no documented validation or sanitization of the CLI output before it is processed by the agent.

antd