telegram-bot-builder

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

• Third-party content exposure detected (high risk: 0.80). The skill clearly ingests untrusted user-generated content from Telegram (e.g., the example handler bot.on('text', (ctx) => { ctx.reply(You said: ${ctx.message.text}); }) in references/patterns.md), so the agent will read and act on arbitrary third‑party messages that could contain injected instructions.