browser-testing-with-devtools

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses Chrome DevTools MCP to read untrusted browser content at runtime (DOM text, console logs, network responses, and JS execution results), which are outsider-authored free text from whatever page the user loads and can be injected into the agent’s LLM context as observations.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime configuration launches an external npm package via npx ("npx -y chrome-devtools-mcp@latest --autoConnect"), which will fetch and execute remote code at runtime and is required for the skill to run.