GTIG AI Threat Tracker, November 2026: an exposed exploit_agent framework automates patch diffing, exploit drafting and execution without a human, a suspected North Korean cluster plants a Claude Code startup download in internal repositories, and PRC-nexus actors stage and exfiltrate through an LLM platform's file hosting
GTIG quarterly: exploit_agent automates n-day exploitation, suspected DPRK cluster abuses .claude/settings.json
Analysis
Three findings from GTIG's quarterly update on adversary use of AI, published 2026-11-16, change what defenders can look for (GTIG, 2026-11-16). First, GTIG identified an exposed staging server hosting a multi-agent vulnerability research and weaponization framework, dubbed exploit_agent, that integrates frontier and local LLMs and runs continuous differential analysis of popular web application software: it compares code before and after patch announcements, analyzes the findings, drafts exploits and executes them automatically, which GTIG says is the first time it has seen LLM frameworks fully automate discovery and exploitation without a human in the loop (GTIG, 2026-11-16). The server also held scripts for internal reconnaissance, brute-forcing, installing web shells and removing other attackers' web shells, and its victim telemetry suggested interest in French media, entertainment and education websites (GTIG, 2026-11-16).
Second, in intrusions against cryptocurrency organizations in North America and Europe, a suspected MIDNIGHT NEPTUNE cluster used fraudulent recruiter profiles, sent targets to fake meeting platforms with ClickFix lures that ran likely LLM-authored staging scripts, and then pivoted into internal code repositories and modified .claude/settings.json so that Claude Code startup triggered the download of the SOMBERMEME backdoor; it masked lateral movement with GitHub personal access tokens named after Microsoft Copilot (GTIG, 2026-11-16). Third, in what GTIG calls a new trend, PRC-nexus actors abused LLM platforms and file-hosting backends for staging, dead-drop command channels and exfiltration, in one case staging lure archives and exfiltrating stolen data through a frontier model's file-hosting infrastructure (GTIG, 2026-11-16). GTIG separately assesses that the open-source agentic pentest frameworks it tracks, among them ARTEX, CAIRN, CyberStrikeAI and PentAGI, currently trade stealth for velocity: they generate forensic traffic, rely on recognizable identifiers and leave distinct code-level traces (GTIG, 2026-11-16).
Cited evidence
In the past quarter, GTIG identified threat actors using LLM frameworks to fully automate vulnerability discovery and exploitation without a human in the loop for the first time.
It compares code before and after patch announcements, analyzes findings to identify potential vulnerabilities, drafts exploits, and automatically executes them without human intervention.
so that when users started up Claude Code, it would automatically trigger the download of the SOMBERMEME backdoor
Sources1
AI-generated · no human review · this permalink is the shareable record for the finding · verify operationally critical claims against the linked primary source.