21st-ui-explore

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the 21st CLI tool to perform project initialization, search for design inspiration, and generate UI components based on fixed constraints.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local configuration files and external search results to inform UI generation. * Ingestion points: Project context is read from .21st/design.json and external references are retrieved via 21st search. * Boundary markers: None explicitly defined in the instructions to separate design data from system prompts. * Capability inventory: Includes shell command execution through the 21st utility (init, search, generate) and local file system interaction. * Sanitization: The workflow relies on the CLI tool's internal logic for processing design tokens and context without additional prompt-level validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 08:13 AM
Security Audit — agent-trust-hub — 21st-ui-explore