playwriter

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly directs the agent to control the user's Chrome via Playwright/Playwriter and navigate arbitrary public websites (e.g., "Use this for JS-heavy websites (Instagram, Twitter...)" and the example page.goto("https://example.com")), which means it will fetch and interact with untrusted, user-generated third‑party content that can influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running the Playwriter CLI at runtime and explicitly recommends fetching and executing remote code via "npx playwriter@latest", which will download and execute an npm package (remote code executed at runtime).