skills/antfu/design/antfu-design/Gen Agent Trust Hub

antfu-design

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands to install necessary development dependencies. Evidence includes pnpm add @antfu/design unocss in references/core-setup.md and multiple pnpm add commands for Storybook integration in references/storybook.md.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download the vendor's design package (@antfu/design) and several well-known third-party libraries (such as unocss, storybook, and vue) from the official NPM registry.
  • [PROMPT_INJECTION]: The skill contains a mechanism to persist design rules into the project's agent configuration, potentially influencing future behavior (Multi-step chain). Ingestion point: The project's AGENTS.md file. Boundary markers: No delimiters or ignore instructions are used when appending the rule. Capability inventory: The skill leverages the agent's file-modification capabilities to persist instructions. Sanitization: No validation or sanitization is performed on the appended content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 03:45 AM
Security Audit — agent-trust-hub — antfu-design