extract-design-system

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions to run shell commands using npx, specifically npx playwright install chromium and npx extract-design-system.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of the extract-design-system package from the NPM registry. Additionally, it downloads Chromium browser binaries via the Playwright library, which is an established tool for web automation.
  • [REMOTE_CODE_EXECUTION]: The use of npx extract-design-system without a specified version string results in the execution of remote code fetched from the NPM registry at runtime. This behavior is central to the skill's primary functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves processing content from external, user-provided websites, which introduces a vulnerability to indirect prompt injection.
  • Ingestion points: The skill ingests data from a public URL using the npx extract-design-system <url> command as specified in SKILL.md.
  • Boundary markers: The skill documentation in SKILL.md and references/workflow.md includes safety instructions to treat third-party website content and the resulting extraction artifacts as untrusted, and to verify any proposed changes with the user.
  • Capability inventory: The skill allows for shell command execution (npx) and local file system modifications within the project's design system directories.
  • Sanitization: There are no specific instructions or mechanisms described for the sanitization of the extracted website content before it is processed or summarized by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 09:22 AM