extract-design
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and execute the
dembrandtpackage from the npm registry usingnpxornpm. This is a vendor-owned resource provided by the skill author for the intended functionality.\n- [COMMAND_EXECUTION]: The skill provides a wide range of shell command examples for design extraction, site crawling, and generating configuration files such as Tailwind or shadcn themes.\n- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves crawling and processing data from external URLs, which represents an attack surface for indirect prompt injection.\n - Ingestion points: External website URLs processed by the tool's headless browser.\n
- Boundary markers: No explicit boundary markers or instructions to ignore embedded content were identified in the skill's guidelines.\n
- Capability inventory: The skill executes shell commands and writes design configuration files to the local system.\n
- Sanitization: No specific sanitization or validation of the extracted design tokens is described within the documentation.
Audit Metadata