aiogram-framework

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

• Third-party content exposure detected (high risk: 0.80). The skill's examples and workflow show receiving and handling arbitrary Telegram updates/messages (e.g., references/quickstart.md's start_polling and the echo handler that reads message.text, plus references/handlers-filters.md describing handlers for user messages), which are untrusted, user-generated third-party content the agent is expected to read and interpret.