21st-design-sync

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill integrates with a known service (21st.dev) using its official CLI tool (@21st-dev/cli).
  • [COMMAND_EXECUTION]: The skill uses npx @21st-dev/cli and 21st publish-theme to perform its primary function. These commands are scoped to the intended purpose of design synchronization.
  • [CREDENTIALS_UNSAFE]: The instructions correctly advise users on secure credential management, recommending the use of environment variables (TWENTYFIRST_TOKEN or API_KEY_21ST) or specific command-line flags. It explicitly instructs the agent not to try to "mint" or generate keys itself, relying on the user to provide a valid API key from the official dashboard.
  • [DATA_EXFILTRATION]: While the skill reads project CSS files and sends them to an external service (21st.dev), it includes a mandatory human-in-the-loop confirmation step before publishing, as themes are public by default. The destination is the vendor's official infrastructure (21st.dev).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 08:56 PM
Security Audit — agent-trust-hub — 21st-design-sync