opentwitter

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

• Third-party content exposure detected (high risk: 1.00). This skill fetches public, user-generated Twitter/X content (e.g., "Get User Tweets" and "Search Twitter" endpoints such as POST https://ai.6551.io/open/twitter_user_tweets and /open/twitter_search) as shown in SKILL.md, so the agent will read untrusted third‑party posts that could materially influence decisions or actions.