lism-mockup-guide
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npxto download and execute the@lism-css/mockuppackage. npm is a well-known and standard package registry. - [COMMAND_EXECUTION]: The workflow requires the execution of shell commands (
npx @lism-css/mockup init,check, anddev) to initialize the environment, verify the code, and start a local development server. - [DYNAMIC_EXECUTION]: The framework bundles and executes React-based JSX/TSX files provided in the data directory. The skill includes an explicit security disclaimer stating that the environment does not use a sandbox and that only trusted mockup code should be executed.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill processes and renders external content from the
pages/directory, along with configuration files likemockup.config.jsonandtokens.json. - Boundary markers: No delimiters or specific safety instructions are provided to the agent for handling the content of the mockup files themselves beyond syntax validation.
- Capability inventory: The skill uses
npxfor package execution and manages a local web server for rendering UI components. - Sanitization: The
checkcommand performs static analysis for schema validity and import boundaries but does not sanitize the logical behavior of the JSX components.
Audit Metadata