marketing-pipeline-auto-content

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

• Third-party content exposure detected (high risk: 0.95). The REQUIRED runtime workflow performs “Research & Content Crawling” by crawling external news/social sources (e.g., TechCrunch, Twitter, LinkedIn) and then injects the resulting research (including content strings) into the LLM prompt via buildPrompt(research, options) → anthropic.messages.create({ content: prompt }), which is outsider-authored free text from public web/social content.