skills/hk-hub/agentskills/shadcn-ui/Gen Agent Trust Hub

shadcn-ui

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a utility script scripts/verify-setup.sh that validates project configuration by performing local read operations on files such as package.json and tsconfig.json.
  • [EXTERNAL_DOWNLOADS]: The skill instructions leverage the official shadcn CLI (npx shadcn@latest) to install components and references standard peer dependencies from the npm registry, including Radix UI and Tailwind CSS.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on project files, presenting a surface for indirect prompt injection. 1. Ingestion points: Reads project configuration and source code (including package.json, tsconfig.json, components.json, and scripts/verify-setup.sh). 2. Boundary markers: No explicit delimiters or protection against embedded instructions are specified in the instructions. 3. Capability inventory: The skill has access to Write, Bash, and web_fetch tools as defined in SKILL.md. 4. Sanitization: The instructions do not define specific mechanisms for sanitizing or validating ingested code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 03:44 AM
Security Audit — agent-trust-hub — shadcn-ui