{
  "id": 19477834,
  "title": "NEAR AI was breached through the engine running its agents, not the prompt",
  "url": "https://urgent.news/2026/11/11/near-ai-was-breached-through-the-engine-running-its-agents-not-the",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-11T09:57:43.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/humanbound_ai/near-ai-was-breached-through-the-engine-running-its-agents-not-the-prompt-3le3"
  },
  "original_language": "en",
  "account": "NEAR AI, an AI platform, suffered a breach due to a flaw in its model-serving engine, SGLang, not from the prompt itself. The attacker obtained code execution on one of NEAR AI's inference servers, then navigated deeper into the infrastructure using an internal system connected to a retired feature. The breach exposed personal information of approximately 100 users, payment details for some users, chat histories, settings, and logs from 18 older agents, as well as AWS API keys for two customers. These compromised keys have since been revoked. NEAR AI paused its cloud inference and promptly rotated credentials following the breach. The attack highlights the importance of scrutinizing the underlying infrastructure, as vulnerabilities in SGLang could potentially compromise the security of AI agents. It is crucial for developers to review and patch their systems, particularly focusing on the software running within the environment, as the isolation provided by such environments does not protect against the code within it.",
  "summary": "Humanbound's engine and CLI are open source: github.com/humanbound/humanbound NEAR AI disclosed on 9 November that an attacker used a remote code execution flaw in SGLang, its model-serving engine, to reach chat histories, settings and logs from 18 agents plus two customers' API keys. On 10 November a policy bypass in the AWS API MCP Server (CVE-2026-125271) was published, and on 11 November…",
  "key_points": [
    "NEAR AI breached via SGLang engine flaw, not prompt",
    "Attack obtained code execution on inference server",
    "Personal data, AWS keys compromised, keys revoked"
  ],
  "editors_take": "Exploiting the underlying model-serving engine rather than the user prompt demonstrates that infrastructure vulnerabilities can bypass traditional isolation to expose sensitive user data and internal system credentials.",
  "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."
}