21st-ui-explore
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the 21st CLI tool to perform initialization, search for design references, and generate interface variants. These operations are aligned with the skill's primary purpose of UI exploration.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific design data and external UI references which could host instructions that influence agent behavior.
- Ingestion points: Project configuration file .21st/design.json and search results from the 21st search command.
- Boundary markers: Absent.
- Capability inventory: Execution of shell commands via the 21st CLI tool.
- Sanitization: No explicit sanitization or validation of the ingested external content is implemented.
Audit Metadata