twitter-to-binance-square

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches public, user-generated tweets from the open web via the 6551 API (see SKILL.md "Step 1: FETCH" and scripts/auto_mirror.py functions fetch_user_tweets/search_tweets), then reads/transforms that untrusted content and uses it to construct and decide posts sent to Binance Square, so third‑party content can materially influence agent actions.