21st-ui-explore
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the project's local environment and external search results.
- Ingestion points: Reads
.21st/design.jsonand project UI source code; processes output from the21st searchcommand. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the prompt templates.
- Capability inventory: The skill is capable of executing shell commands via the
21stCLI (init,search,generate) and writing configuration data back to the file system. - Sanitization: There is no evidence of sanitization or content validation for the data ingested from the project UI or search results.
- [COMMAND_EXECUTION]: The skill instructions specify the execution of several shell commands using the vendor-provided CLI tool.
- Evidence: The workflow in
SKILL.mdincludes21st init --design-context,21st search "<interface and product context>" --context auto, and21st generate "<goal plus fixed constraints>" --context auto --variants 3.
Audit Metadata