Google Threat Intelligence Group reported that cybercriminals planned a mass-exploitation campaign using a two-factor-authentication bypass in an open-source web administration tool, and assessed with high confidence that an AI model supported discovery and weaponization of the flaw. GTIG worked with the vendor on disclosure and disrupted the activity. The same report describes PRC-nexus actors using agentic frameworks such as Hexstrike and Strix for reconnaissance and vulnerability validation, and Android malware (PROMPTSPY) that calls Gemini to drive the device UI.
Why it matters
GTIG calls it the first identified instance of a zero-day exploit it believes was AI-developed by cybercrime actors.
Key facts
As stated in the sources, with where to find them.
- GTIG assessed with high confidence that an AI model supported discovery and weaponization of a 2FA-bypass logic flaw; it states it does not believe Gemini was used.AI-developed zero-day section
- A suspected PRC-nexus actor used Hexstrike (with a knowledge-graph memory) and the Strix multi-agent pentest framework against a Japanese technology firm and an East Asian security platform.Hexstrike and Strix section
- UNC6780 (TeamPCP) supply-chain compromises touched repositories including LiteLLM, Trivy and Checkmarx.Supply chain section
Findings that cite this record
Key questions this bears on
- Where are deployed AI agents actually being exploited?Exploitation often reaches deployed agents through connectors, credentials, tools and packages.
- How are attackers using AI agents in real operations?To run large parts of intrusions under human direction, including espionage, credential theft and extortion; reported autonomy and success vary.
Sources
Related records
Sep 8, 2026
May 11, 2026
Nov 5, 2025
Jan 29, 2025
Oct 30, 2026
Sep 30, 2026