playwright-skill

Warn

Audited by Snyk on Mar 31, 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). The skill explicitly browses and scrapes arbitrary web pages (e.g., page.goto(...) and link-checking examples in SKILL.md, the scraping helpers extractTexts/extractTableData/handleCookieBanner in scripts/lib/helpers.js, and the universal executor scripts/run.js which runs user scripts or inline code that can navigate to external URLs), so untrusted third‑party page content is read and can influence automation decisions and subsequent actions.

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

  • Potentially malicious external URL detected (high risk: 0.70). scripts/run.js invokes runtime installers (execSync('npm install' and 'npx playwright install chromium')), which will fetch and execute packages from the npm registry (https://registry.npmjs.org/) and Playwright browser download endpoints, so the skill depends on remote code fetched at runtime.

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
Mar 31, 2026, 07:06 PM
Issues
2