shadcn-ui

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The maintenance script (scripts/check-updates.py) fetches version metadata from the official npm registry (registry.npmjs.org). This is a legitimate operation for verifying documentation accuracy.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute the shadcn CLI using npx, allowing it to initialize project configurations and manage component installation.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents the tool's ability to install components from external URLs. This introduces a surface where a user-provided URL could lead to the download of untrusted content. 1. Ingestion points: Command examples in SKILL.md and references/01-cli.md accepting URLs. 2. Boundary markers: No explicit instructions for URL validation are provided. 3. Capability inventory: Shell execution via npx. 4. Sanitization: None provided for external registry URLs.
  • [SAFE]: No malicious behavior, obfuscation, or data exfiltration was identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:30 AM
Security Audit — agent-trust-hub — shadcn-ui