twitter

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches user-generated Twitter/X content from the public twitterapi.io API (see API_BASE in scripts/twitter_api.py and the SKILL.md commands like search_tweets.py, get_tweet_replies.py, get_user_tweets.py, get_community_tweets.py), and those tweets/replies/posts are ingested and processed by the scripts as part of normal workflow, so untrusted third‑party content could indirectly supply instructions that influence agent behavior.