NYC
skills/smithery/ai/shadcn-ui/Gen Agent Trust Hub

shadcn-ui

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses the Bash tool to execute npx, rm, and a local project script (../scripts/safe-start.sh). These operations are necessary for the primary purpose of managing UI components and restarting the development environment.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill invokes npx shadcn@2.3.0, which downloads the ShadCN CLI from the official npm registry. This is a standard development practice for adding UI libraries.
  • [PROMPT_INJECTION] (SAFE): The skill interpolates user-provided component names into shell commands. While this creates a vulnerability surface for indirect prompt injection, it is essential for the skill's functionality and is considered safe within the context of developer-led component installation.
  • Ingestion points: {component} variable in the installation and deletion commands.
  • Boundary markers: Absent; the component name is directly interpolated.
  • Capability inventory: File system modification (rm), external package execution (npx), and local script execution.
  • Sanitization: Absent; the skill relies on the user providing valid component names.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:44 PM