x-viral-topic

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

• Third-party content exposure detected (high risk: 0.85). Yes—scripts/search_x_viral_topic.py fetches outsider-authored tweet JSON from the runtime URL https://api.twitterapi.io/... (public web/API content), then reads tweet text/full_text into summary/title and includes it in the script’s Markdown/JSON output (e.g., format_markdown uses item.get('summary')), which would be fed into the agent/LLM context if the agent consumes that output.