tg

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

• Third-party content exposure detected (high risk: 0.90). The skill directly reads and searches Telegram user messages and chats (e.g., via commands like "tg read", "tg search", and "tg inbox"), ingesting user-generated content from Telegram — an untrusted third-party source that could carry indirect prompt injections.