# Researchers uncover security flaw in Google AI chatbot > Source: > Published: 2026-07-07 13:33:10+00:00 # Researchers uncover security flaw in Google AI chatbot A landmark GTIG report documents the first known case of criminals using AI to discover and weaponize a zero-day exploit, raising fresh questions about the security of AI systems themselves The line between AI as a productivity tool and AI as a weapon just got a lot blurrier. On May 11, 2026, Google’s Threat Intelligence Group published a report documenting something the security community had long feared but never confirmed: a criminal actor using an AI model to discover a zero-day vulnerability and then build a working exploit around it. Zero-days, which are software flaws unknown to the vendor and therefore unpatched, have historically required deep human expertise to uncover. ## What actually happened The exploit targeted a Python script tied to two-factor authentication bypass in a widely used open-source system administration tool. Google stated it had “high confidence” that an AI model played a central role in both discovering the flaw and developing the weaponized code. That confidence assessment came from analyzing the code structure, comments, and other technical indicators left behind in the exploit. One important clarification from Google: the AI model used by the attackers was not Gemini, the company’s own chatbot product. The planned mass exploitation was stopped before it could be widely deployed. ## Gemini’s own vulnerabilities are a separate problem In September 2025, security firm Tenable disclosed three vulnerabilities in Gemini related to private data exfiltration. Those flaws were later remediated, but the disclosure window meant that sensitive information processed through Gemini could, under certain conditions, have been siphoned out without user awareness. Then in March 2026, Palo Alto Networks reported CVE-2026-0628, a high-severity privilege escalation vulnerability in the Gemini side panel built into Chrome. Google did move to expand its AI Vulnerability Reward Program in October 2025, creating financial incentives for outside researchers to find and report AI-related security issues. ## What this means for the broader tech and crypto landscape There are no direct crypto market implications documented in connection with these specific incidents. No tokens, no protocols, no blockchain infrastructure was named as a target or a casualty. The specific exploit documented by GTIG targeted a system administration tool’s 2FA mechanism. Two-factor authentication is a primary security layer for virtually every centralized crypto exchange. **Disclosure:** This article was edited by Editorial Team. For more information on how we create and review content, see our [Editorial Policy](https://cryptobriefing.com/editorial-policy/).