telegram

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

• Third-party content exposure detected (high risk: 0.80). The skill ingests untrusted, user-generated Telegram messages (via the Claudicle daemon adapter /telegram_listen.py and by reading ~/.claudicle/daemon/inbox.jsonl) which are processed by the /telegram-respond cognitive pipeline and can drive automated responses, so third-party content could influence agent actions.