extract-page-data

Warn

Audited by Snyk on May 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly opens arbitrary user-supplied web URLs (extract.mjs takes a and openPage uses Playwright to navigate), injects and evaluates page scripts (scripts/inject/*.js via page.evaluate) to extract design tokens, Markdown, and links, and then uses those extracted artifacts (theme.json, content.md, links.json and the "Theme Clone Workflow" in SKILL.md) to drive interpretation and reconstruction actions—therefore it consumes untrusted third-party content at runtime that can materially influence subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill's ensureDependencies routine runs npm/npx to install Playwright and to download Chromium at runtime (including a fallback that sets PLAYWRIGHT_DOWNLOAD_HOST=https://npmmirror.com/mirrors/playwright), which fetches and installs remote binaries/packages that will be executed and are required for the skill to run.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 20, 2026, 06:31 AM
Issues
2
Security Audit — snyk — extract-page-data