playwright-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill includes and exemplifies hardcoded plaintext credentials in generated Playwright scripts (e.g., filling passwords like 'password123'), which encourages embedding real secrets verbatim in outputs and thus creates exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly navigates to and inspects arbitrary webpages (e.g., page.goto(TARGET_URL) in the "Reconnaissance-Then-Action" pattern and examples like navigating to https://example.com and iterating a[href^="http"] with page.request.head), reads DOM textContent/attributes, and then makes automation decisions (clicks, form fills, etc.), which clearly ingests untrusted third-party web content that can influence actions.