skills/21st-dev/skill/21st-ui-build/Gen Agent Trust Hub

21st-ui-build

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using the 21st CLI tool (including 21st init, 21st search, 21st generate, and 21st review) to manage design contexts, retrieve components, and perform code reviews. This is standard functionality for the vendor's toolset.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local project files and tool outputs which could potentially serve as a vector for indirect prompt injection.
  • Ingestion points: The agent reads .21st/design.json, .21st/DESIGN.md, and the results returned by 21st search to inform its UI generation.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the workflow.
  • Capability inventory: The skill possesses the ability to execute shell commands via the 21st tool and modify files within the project directory.
  • Sanitization: No explicit sanitization or validation logic is defined for the ingested project configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 09:32 PM
Security Audit — agent-trust-hub — 21st-ui-build