telegram

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and formats Telegram messages (user-generated content) via scripts/telegram_fetch.py (functions like fetch_recent, search_messages, fetch_thread_messages) and SKILL.md states the output is "formatted markdown suitable for Claude to read and summarize," so untrusted third‑party content is ingested and can influence subsequent actions (e.g., replies, sends, publishes).