marketing-social

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

• Third-party content exposure detected (medium risk: 0.30). The workflow’s Research Mode explicitly uses agent-browser to open and extract readable text from outsider-authored social pages (e.g., Instagram/TikTok/LinkedIn/Explore) such as agent-browser get text body after visiting attacker-controlled handles or trending pages.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs at runtime to install an external package via "npx skills add https://github.com/vercel-labs/agent-browser" (https://github.com/vercel-labs/agent-browser), which fetches and installs remote code the skill relies on for agent-browser-based research.