twitter

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

• Third-party content exposure detected (high risk: 0.90). This skill calls twitterapi.io from scripts/twitter_api.py (API_BASE = "https://api.twitterapi.io/twitter") and numerous scripts (e.g., get_tweet.py, get_user_tweets.py, search_tweets.py, get_community_tweets.py) fetch and print tweets, replies, bios, and community posts — all user-generated public content — so the agent consumes untrusted third-party content that could contain indirect prompt injections.