marketing-paid-ads

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow’s “Research Mode: Competitive Ad Intelligence” uses agent-browser to open and read competitor-supplied/free-text web page content at URLs like the Meta Ad Library, Google Ad Transparency Center, TikTok Creative Center, and {competitor-landing-page-url}, then extracts text body for analysis.

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

• Potentially malicious external URL detected (high risk: 0.90). The shared-patterns setup instructs installing an external CLI at runtime using "npx skills add https://github.com/vercel-labs/agent-browser", which fetches and executes remote code that the skill relies on for browser-based research.