marketing-video

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

• Third-party content exposure detected (low risk: 0.10). The required workflow only reads first-party local brand/context files (e.g., ./brands/{brand-slug}/...) and trusted reference markdown, with optional live URL audit limited to user-provided page content and no step that indiscriminately monitors outsider-authored feeds/queues.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill recommends installing and running code from a remote git URL at runtime via "npx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser", which fetches and executes external code (https://github.com/vercel-labs/agent-browser).