twitter-threads

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is to call TikHub endpoints (e.g., fetch_search_timeline, fetch_user_posts, fetch_post_comments) that return Twitter/X/Threads content authored by third parties, which the agent would then ingest as readable text into the LLM context (indirect prompt-injection risk from outsider social media text).