Social Media Content Extraction

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly scrapes public, user-generated content from Threads and Instagram (via mcp_hyperbrowser_scrape_webpage and reply crawling) and ingests/post-processes those posts and replies, exposing the agent to untrusted third-party content that could contain indirect prompt injection.