21st-ai

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [SAFE]: The skill facilitates interaction with the official 21st AI service using the vendor's '@21st-dev/cli' tool.
  • [COMMAND_EXECUTION]: The skill documents the use of '21st generate', '21st iterate', and '21st take' commands to manage UI generation projects via the terminal.
  • [CREDENTIALS_UNSAFE]: The skill describes authentication via '21st login' and environment variables like 'TWENTYFIRST_TOKEN'. It provides examples of API key patterns ('21st_sk_') but does not contain any hardcoded secrets or sensitive credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 06:55 AM
Security Audit — agent-trust-hub — 21st-ai