add-telegram

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

• Third-party content exposure detected (high risk: 1.00). The skill’s runtime path ingests outsider-authored free text from Telegram users via this.bot.on("message:text", ...) reading ctx.message.text and then passing it into the agent through this.opts.onMessage(chatJid, { content, ... }) → storeMessage(msg) → processGroupMessages → LLM context.