Twitter/X Automation

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime “Engage”/“Auto-Engagement” workflows (e.g., reply_to_mentions, engage_with_niche via search_hashtags) necessarily ingest outsider-authored tweet/mention text from Twitter/X into the agent so it can decide how to like/reply, which is free-form user-generated content.