{
  "id": 5208980,
  "title": "Capsule Security fine-tunes Nvidia Nemotron models to stop rogue AI agents",
  "url": "https://urgent.news/2026/09/03/capsule-security-fine-tunes-nvidia-nemotron-models-to-stop-rogue-ai",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-03T00:24:35.000Z",
  "source": {
    "name": "SiliconANGLE",
    "slug": "siliconangle",
    "url": "https://siliconangle.com/2026/09/02/capsule-security-fine-tunes-nvidia-nemotron-models-to-stop-rogue-ai-agents/"
  },
  "original_language": "en",
  "account": "Capsule Security, an agentic artificial intelligence security startup, has unveiled a detection system utilizing Nvidia Corp.'s Nemotron models, fine-tuned specifically for the purpose. This system, dubbed the \"AI circuit breaker,\" operates by judging an agent's intended action in real-time before execution. Customers can subsequently allow, flag, or block the action in real-time, thereby establishing a control layer external to the agent. This mechanism is designed to address the increasing prevalence of agents with access to sensitive data, source code, or production infrastructure. The system utilizes two of Nvidia's largest Nemotron models, Nemotron 3 Ultra, and Nemotron 3, which are capable of running within an agent's workflow without significantly hindering performance. According to Capsule Security, the system achieved 98% accuracy on the StepShield benchmark, a metric for detecting rogue agent behavior at the step level. The benchmark utilized 9,429 code-agent trajectories derived from real incidents. While the startup acknowledges that rule-based guardrails can be effective, they often result in a high number of false positives. In contrast, the fine-tuned models used by Capsule can classify a narrow set of actions with high precision and speed, making real-time decisions in as little as 71 milliseconds. The company claims that billions of tokens across millions of agent interactions are currently processed using this technology, with customers ranging from financial institutions to technology companies. The startup's co-founders, Naor Paz and Lidan Hazout, emphasize that the core AI security risk now lies not just in what people can do with agents, but in what autonomous agents decide to do on their own. The release of this system follows the disclosure of two prompt injection vulnerabilities in widely used AI tools by Microsoft and Salesforce, both of which have since been patched.",
  "summary": "Agentic artificial intelligence security startup Capsule Security Ltd. today released a detection system built on two Nvidia Corp. Nemotron models it fine-tuned itself, in what it calls an “AI circuit breaker” for rogue AI agents. The models judge an agent’s intended action in the moment before it executes. Customers can then allow it, flag it […] The post Capsule Security fine-tunes Nvidia…",
  "key_points": [
    "Capsule Security develops AI circuit breaker using Nvidia Nemotron models.",
    "System achieves 98% accuracy on StepShield benchmark for rogue agent detection.",
    "Customers process billions of tokens with real-time action control."
  ],
  "editors_take": "Capsule Security's fine-tuned Nvidia Nemotron models enable real-time detection and control of rogue AI agents, addressing growing security risks as agents gain access to sensitive data and infrastructure.",
  "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."
}