antd
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the @ant-design/cli package globally from the npm registry if it is not already available. This package is the official tool provided by the Ant Design scope for these tasks.
- [COMMAND_EXECUTION]: The skill makes extensive use of the antd CLI tool to perform various shell-based operations, including querying component props, retrieving demos, linting project files, and generating bug reports.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its interaction with external, untrusted project data.
- Ingestion points: The agent reads and processes the contents of the local ./src directory when executing antd lint and antd usage commands.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the analyzed source code and its own operational guidelines.
- Capability inventory: The skill allows for the execution of arbitrary shell commands via the CLI and the submission of data to external endpoints through bug reporting features.
- Sanitization: The skill does not specify any sanitization or validation steps for the content ingested from the project files prior to processing.
Audit Metadata