marketing-cro

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

• Third-party content exposure detected (medium risk: 0.30). In “Research Mode: Live Page Auditing”, the workflow uses agent-browser ... open "https://{page-url}" and then runs agent-browser get text body, so outsider-authored HTML/text from a user-supplied live URL is ingested at runtime before recommendations are produced.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime agent-browser setup explicitly instructs installing code from https://github.com/vercel-labs/agent-browser via an npx command, which fetches and executes remote code and is required for the skill's Research Mode, so this external URL is a runtime dependency that executes remote code.