chrome-devtools-mcp-automation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to navigate to arbitrary public URLs and extract/execute page content (e.g., the "Web Scraping" example using browser_navigate to https://news.example.com and browser_evaluate to read article text), so the agent will ingest untrusted third‑party webpage content that could contain malicious or instructional payloads influencing subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx chrome-devtools-mcp@latest", which at runtime fetches and executes remote code from the npm registry (the chrome-devtools-mcp package), so this external package fetch is a required runtime dependency that executes remote code.