telegram-bot-api-fundamentals

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime path ingests OUTSIDER-authored free text from Telegram updates—e.g., Update.message.text (user messages) is parsed and then used in the agent’s LLM context via handlers like bot.command(...) / ctx.reply(...) (the user’s text is not authored by the operating user).