bklit-ui-design
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from user design requests and local project environment files such as package.json and CSS. \n
- Ingestion points: Local project files analyzed by the
scripts/detect-design.mjsutility and natural language prompts from the user. \n - Boundary markers: There are no explicit delimiters or safety instructions defined in the workflow to isolate external data from the agent's logic. \n
- Capability inventory: The skill uses shell execution capabilities to run local scripts (
node) and package managers (npx shadcn). \n - Sanitization: The skill does not describe any sanitization or validation mechanisms for the data ingested from the project filesystem or user input before processing.
Audit Metadata