grammy

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly ingests untrusted, user-generated content from Telegram (e.g., bot.on("message") handlers, conversation.wait() reading message.text, and API calls like fetch to https://api.telegram.org in bin/*.ts) and the examples show the agent reading and acting on that content as part of its workflow, so third-party messages could indirectly inject instructions.