AI · Article
Google Finds AI Agent That Writes Exploits From Patches Without Human Help
사이언스모니터 ·

At a glance
Google's threat intelligence team said it found a multi-agent hacking framework called exploit_agent on an exposed staging server. It studies security patches to find flaws, writes attack code, and runs it without people involved.
Key points
- Google's threat intelligence group found the exploit_agent framework on an exposed test server.
- The tool compares code before and after security patches to find flaws and write attack code.
- Attackers ran it automatically without human involvement.
- The number of zero-day flaws exploited rose from about 8 a month in 2025 to 11 a month in 2026.
Why it matters
If attackers can turn patches into attacks automatically, users have less time to install fixes before they are targeted.
Original source
구글 “AI 에이전트가 패치 분석해 스스로 공격”…사람 없는 자동 해킹 첫 확인
사이언스모니터 · Nov 17, 11:22 KST
Read on 사이언스모니터 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to 사이언스모니터.
Other coverage
Google · Ranking and more news
More from this field
- Anthropic Mathematician Says Claude Helped Crack the Riemann Hypothesis
A video about a claim that an Anthropic mathematician, Levent Alpöge, used Claude to find a proof of the Riemann Hypothesis in about six weeks. The creator skips the heavy math and looks at what this could mean for AI and its future. The proof is still being checked.
TheAIGRID · Nov 21, 08:45 KST - Google Brings Duplex Calling to Gemini, Letting AI Phone Businesses for You
Google has moved its Duplex phone-calling technology into the Gemini app, so Gemini can now call businesses for you. The system has changed a lot since 2018, shifting from narrow custom models to a single stack built on Gemini.
Google Research blog · Nov 21, 08:30 KST - Google Releases Project Genie, an AI That Generates Explorable Worlds
Google has released Project Genie, an AI tool that creates interactive worlds you can explore. The video shows how to access it, walks through a generated world and a T-Rex demo, and discusses why this early technology matters.
The AI Advantage · Nov 21, 08:21 KST - Anthropic Employee Says Claude Helped Prove Riemann Hypothesis
An Anthropic employee and mathematician, Levent Alpöge, says he used the company's Claude chatbot to create a detailed proof of the Riemann hypothesis over about six weeks. The proof has not yet been checked, and it is over 250,000 lines long in Lean, a computer language used to confirm maths proofs.
BBC News · Nov 21, 08:08 KST