chrome-bridge-automation

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

• Third-party content exposure detected (low risk: 0.10). The agent navigates to arbitrary web pages using the browser automation tool, which exposes it to outsider-authored free text via web page content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to run npx @midscene/web@1, which executes a remote package fetched dynamically at runtime from the public npm registry, constituting an unverifiable external operational dependency.