marketing-influencer

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 uses agent-browser to open third-party social pages/creator profiles (e.g., TikTok search, Instagram hashtag pages, YouTube results) and then runs agent-browser get text body, so outsider-authored free text from those pages is ingested at runtime.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's setup requires installing the agent-browser package via npx from https://github.com/vercel-labs/agent-browser, which fetches and executes remote code at install time and is relied upon by the skill's runtime agent-browser commands.