{
  "id": 17753384,
  "title": "I Hacked Every AI Voice Agent at a #1 Product Hunt Company's Launch Hackathon",
  "url": "https://urgent.news/2026/11/02/i-hacked-every-ai-voice-agent-at-a-1-product-hunt-companys-launch",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-02T05:48:48.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/billasur/i-hacked-every-ai-voice-agent-at-a-1-product-hunt-companys-launch-hackathon-o34"
  },
  "original_language": "en",
  "account": "A hackathon hosted by Vaani, a high-speed infrastructure company for enterprise voice agents, saw reporter hijack every AI voice agent in the platform. The attacker, using only a free account and one HTTP request, was able to silently hijack outbound phone lines and read malicious instructions from an attacker. Vaani's multi-tenant voice AI is a ticking time bomb if the architecture is flawed.",
  "summary": "What is the worst thing an attacker can do to your company? Leak a database? Deface your landing page? Drain your ad account? How about silently hijacking your outbound phone lines, so your AI voice bots dial your highest-paying clients and read malicious instructions from an attacker, live, in real time, with zero warning? If you are building or deploying AI agents today, you might be sitting on…",
  "key_points": [],
  "editors_take": "The ability to hijack outbound lines with a single request exposes a critical architectural flaw that turns multi-tenant voice infrastructure into a massive security liability for enterprise users.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}