marketing-paid-ads

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Research Mode" (SKILL.md) explicitly instructs use of agent-browser to open and scrape public third-party pages — e.g., Facebook Ads Library, Google Ad Transparency Center, TikTok Creative Center, competitor landing pages/pricing URLs — and to "get text body" for extraction and competitive analysis, which the agent will read and use to drive campaign decisions, exposing it to untrusted user-generated/open-web content that could carry indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's Research Mode directs installation and use of agent-browser via an install command that fetches and runs remote code (e.g., npx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser), which is a required dependency for live competitor research and thus can execute remote code during setup/runtime.