LOWAi
Global

Researchers Use Claude to Port Pre-Auth RCE Exploit From One PLC Model to Another

·Source: The Hacker News

Updated:

Executive Summary

Forescout Research - Vedere Labs said it used Anthropic's Claude to port a working pre-authentication remote code execution (RCE) exploit from one WAGO programmable logic controller (PLC) to another, executing attacker-supplied ARM shellcode on live hardware. The exploit targets CVE-2021-31886, a stack-based buffer overflow in the Nucleus FTP server's handling of the USER command

Analysis

Forescout Research - Vedere Labs said it used Anthropic's Claude to port a working pre-authentication remote code execution (RCE) exploit from one WAGO programmable logic controller (PLC) to another, executing attacker-supplied ARM shellcode on live hardware. The exploit targets CVE-2021-31886, a stack-based buffer overflow in the Nucleus FTP server's handling of the USER command

Indicators of Compromise (1)

CVE (1)
CVE-2021-31886
Source Attribution

Originally published by The Hacker News on Sep 2, 2026.

Related Threats

CRITICALZero Day

What happens when AI models take aim at ICS exploits

LLMs have shown great improvement in vulnerability research and exploit development capabilities over the past six months. But it’s one thing to find vulnerabilities in well documented open-source projects and an entirely different skillset to decrypt file systems and reverse-engineer closed-source low-level firmware in highly specialized embedded devices. That’s why researchers from industrial Io

CVE-2025-67038CVE-2021-31886
CSO Online
MEDIUMAi

Palo Alto's $4.5B Applied Compute Purchase Targets AI Risks

<img src="https://ismg-cdn.nyc3.cdn.digitaloceanspaces.com/articles/palo-altos-45b-applied-compute-purchase-targets-ai-risks-image_small-3-a-33443.jpg" align=right hspace=4><b>Applied Compute Deal Aims to Replace Static Controls With AI-Powered Supervision</b><br>Palo Alto Networks plans to acquire Applied Compute for $4.5 billion to develop advanced reasoning models that detect and stop unsafe AI

Bank Info Security
CRITICALAi

AI unearths ‘internet breaker’ flaws in Nginx web server

Nginx, the web server estimated to power a third of the internet, has shipped fixes for multiple vulnerabilities, including a critical unauthenticated remote code execution flaw that puts millions of websites at risk and has existed in the code for over a decade. Researchers from several security firms independently found some of the same flaws by using AI agents, adding to a string of recent AI-d

CVE-2026-123007CVE-2026-123633
CSO Online