extract-design

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the global installation of the dembrandt npm package, which is a resource provided by the author.
  • [COMMAND_EXECUTION]: The instructions include various CLI commands for the dembrandt tool used to analyze websites and save design metadata.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its core function of ingesting data from untrusted external websites.
  • Ingestion points: Untrusted content is read from user-provided URLs.
  • Boundary markers: No explicit delimiters are used to wrap the extracted design data or warn the agent to ignore embedded instructions.
  • Capability inventory: The agent uses the extracted data to construct configuration files for frameworks like Tailwind and shadcn/ui.
  • Sanitization: The skill does not describe any sanitization or validation processes for the data retrieved from external DOM elements.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 01:58 PM