antd
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill initiates the installation of the
@ant-design/clipackage from the public npm registry if it is not already present. This package is an official tool provided by the 'ant-design' organization for managing component metadata and project analysis. - [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to executeantdCLI commands. These operations are scoped to documentation queries (info,doc), project analysis (usage,doctor), and code linting (lint). The execution is restricted via theallowed-toolsmetadata field. - [DATA_EXFILTRATION]: The skill contains functionality to report bugs using the
antd bugandantd bug-clicommands. This involves sending user-provided descriptions and reproduction steps to an external endpoint. The instructions enforce a safety protocol requiring the agent to preview the report and obtain explicit user confirmation before the final submission. - [PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by reading and analyzing untrusted project data through
antd usageandantd lint. - Ingestion points: Local source files in
./src(read viaantd usageandantd lint). - Boundary markers: None explicitly defined in the prompt instructions.
- Capability inventory: Shell command execution via
Bashtool. - Sanitization: Not specified within the skill instructions.
Audit Metadata