{"slug": "google-says-an-ai-framework-turned-security-patches-into-exploits-with-no-human", "title": "Google says an AI framework turned security patches into exploits with no human in the loop", "summary": "Google Threat Intelligence Group reported that attackers for the first time used an AI framework, called exploit_agent, running with no human in the loop to convert security patches into exploits. The framework was found on an exposed staging server, where it was connected to several other systems, according to the Google report. The finding marks the first documented case of an autonomous AI agent producing working exploits from patch information without human involvement.", "body_md": "# Google says an AI framework turned security patches into exploits with no human in the loop\n\nBy Duncan RileySource: \n\n[SiliconANGLE](https://siliconangle.com)\nA new report out today from Google LLC’s Google Threat Intelligence Group finds that for the first time, attackers have used an [artificial intelligence](https://www.machinebrief.com/glossary/artificial-intelligence) framework running with no human in the loop to turn security patches into exploits. Called exploit_agent, the framework turned up on an exposed staging server, where it was wired into several […]\n\nThe post [Google says an AI framework turned security patches into exploits with no human in the loop](https://siliconangle.com/2026/11/16/google-says-an-ai-framework-turned-security-patches-into-exploits-with-no-human-in-the-loop/) appeared first on [SiliconANGLE](https://siliconangle.com).\n\nGet AI news in your inbox\n\nDaily digest of what matters in AI.", "url": "https://wpnews.pro/news/google-says-an-ai-framework-turned-security-patches-into-exploits-with-no-human", "canonical_source": "https://www.machinebrief.com/news/google-says-an-ai-framework-turned-security-patches-into-exp-2wf9", "published_at": "2026-11-16 14:00:47+00:00", "updated_at": "2026-11-16 14:52:40.807928+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "ai-agents"], "entities": ["Google", "Google Threat Intelligence Group", "exploit_agent", "SiliconANGLE", "Duncan Riley"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/google-says-an-ai-framework-turned-security-patches-into-exploits-with-no-human", "markdown": "https://wpnews.pro/news/google-says-an-ai-framework-turned-security-patches-into-exploits-with-no-human.md", "text": "https://wpnews.pro/news/google-says-an-ai-framework-turned-security-patches-into-exploits-with-no-human.txt", "jsonld": "https://wpnews.pro/news/google-says-an-ai-framework-turned-security-patches-into-exploits-with-no-human.jsonld"}}