interacting-with-x

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly reads public, user-generated X (Twitter) content — see scripts/read.py (get_timeline, get_mentions, get_user_tweets, search_tweets) which fetches tweets via the X API and formats/outputs their text for the agent to read, exposing it to untrusted third‑party input that could enable indirect prompt injection.