CTIPilot
AI-generated · no human review · verify critical claims against the linked source. how it works →

exploit_agent

tool · tool:exploit-agent-gtig single-source

Name GTIG gives to an exposed multi-agent vulnerability research and weaponization framework that compares code before and after patch announcements, drafts exploits and executes them without human intervention (GTIG, 2026-11-16).

Coverage
1
first 2026-11-17 → last 2026-11-17
Latest activity
2026-11-17
GTIG quarterly: exploit_agent automates n-day exploitation, suspected DPRK cluster abuses…
Peak priority
notable
1 notable
Targets
technology
sectors: technology
Sources cited
1
1 hosts

Defender insights

What each entry about exploit_agent tells a defender to do, newest first.

2026-11-17NOTABLEGTIG quarterly: exploit_agent automates n-day exploitation, suspected DPRK cluster abuses .claude/settings.json

Exposure · detection

Relationships explore in graph

Typed, source-stated connections from the entity registry; each edge cites the entry whose reporting establishes it.

documented in

Story timeline

  1. 2026-11-17GTIG 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
    researchGTIG quarterly: exploit_agent automates n-day exploitation, suspected DPRK cluster abuses .claude/settings.json
ATT&CK techniques (9 across 7 tactics)

9 techniques observed across 1 entry about this entity, derived from entry metadata and body evidence, never asserted without a published entry behind it · pinned to MITRE ATT&CK v20.1 · compare on the matrix · Navigator layer (JSON)

  • Resource DevelopmentDevelop Capabilities: Exploits
  • Initial AccessExploit Public-Facing Application · Supply Chain Compromise: Compromise Software Dependencies and Development Tools · Phishing: Spearphishing via Service
  • ExecutionUser Execution: Malicious Copy and Paste
  • PersistenceAccount Manipulation: Additional Cloud Credentials · Server Software Component: Web Shell
  • Privilege EscalationAccount Manipulation: Additional Cloud Credentials
  • Command and ControlWeb Service
  • ExfiltrationExfiltration Over Web Service

Resource Development TA0042

T1587.004Develop Capabilities: Exploits×1

Adversaries may develop exploits that can be used during targeting. An exploit takes advantage of a bug or vulnerability in order to cause unintended or unanticipated behavior to occur on computer hardware or software. Rather than finding/modifying exploits from online or purchasing them from exploit vendors, an adversary may develop their own exploits. Adversaries may use information acquired via Vulnerabilities to focus exploit development efforts. As part of the exploit development process, adversaries may uncover exploitable vulnerabilities through methods such as fuzzing and patch analysis.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

Initial Access TA0001

T1190Exploit Public-Facing Application×1

Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network. The weakness in the system can be a software bug, a temporary glitch, or a misconfiguration.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

T1195.001Supply Chain Compromise: Compromise Software Dependencies and Development Tools×1

Adversaries may manipulate software dependencies and development tools prior to receipt by a final consumer for the purpose of data or system compromise. Applications often depend on external software to function properly. Popular open source projects that are used as dependencies in many applications, such as pip and NPM packages, may be targeted as a means to add malicious code to users of the dependency. This may also include abandoned packages, which in some cases could be re-registered by threat actors after being removed by the original owner. Adversaries may also employ "typosquatting" or name-confusion by choosing names similar to existing popular libraries or packages in order to deceive a user.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

T1566.003Phishing: Spearphishing via Service×1

Adversaries may send spearphishing messages via third-party services in an attempt to gain access to victim systems. Spearphishing via service is a specific variant of spearphishing. It is different from other forms of spearphishing in that it employs the use of third party services rather than directly via enterprise email channels.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

Execution TA0002

T1204.004User Execution: Malicious Copy and Paste×1

An adversary may rely upon a user copying and pasting code in order to gain execution. Users may be subjected to social engineering to get them to copy and paste code directly into a Command and Scripting Interpreter. One such strategy is "ClickFix," in which adversaries present users with seemingly helpful solutions (such as prompts to fix errors or complete CAPTCHAs) that instead instruct the user to copy and paste malicious code.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

Persistence TA0003

T1098.001Account Manipulation: Additional Cloud Credentials×1

Adversaries may add adversary-controlled credentials to a cloud account to maintain persistent access to victim accounts and instances within the environment.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

T1505.003Server Software Component: Web Shell×1

Adversaries may backdoor web servers with web shells to establish persistent access to systems. A Web shell is a Web script that is placed on an openly accessible Web server to allow an adversary to access the Web server as a gateway into a network. A Web shell may provide a set of functions to execute or a command-line interface on the system that hosts the Web server.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

Privilege Escalation TA0004

T1098.001Account Manipulation: Additional Cloud Credentials×1

Adversaries may add adversary-controlled credentials to a cloud account to maintain persistent access to victim accounts and instances within the environment.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

Command and Control TA0011

T1102Web Service×1

Adversaries may use an existing, legitimate external Web service as a means for relaying data to/from a compromised system. Popular websites, cloud services, and social media acting as a mechanism for C2 may give a significant amount of cover due to the likelihood that hosts within a network are already communicating with them prior to a compromise. Using common services, such as those offered by Google, Microsoft, or Twitter, makes it easier for adversaries to hide in expected noise. Web service providers commonly use SSL/TLS encryption, giving adversaries an added level of protection.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

Exfiltration TA0010

T1567Exfiltration Over Web Service×1

Adversaries may use an existing, legitimate external Web service to exfiltrate data rather than their primary command and control channel. Popular Web services acting as an exfiltration mechanism may give a significant amount of cover due to the likelihood that hosts within a network are already communicating with them prior to compromise. Firewall rules may also already exist to permit traffic to these services.

Evidence: 2026-11-17/gtig-ai-threat-tracker-nov-2026-exploit-agent-settings · ATT&CK page ↗

Entries about exploit_agent (1)

2026-11-17 · view entry permalink →

NOTABLENATOB2

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

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).

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

Google Threat Intelligence Group / Mandiant 2026-11-16
annual-report17 Nov 04:41Zsingle-sourceOpen finding →

Where this entity is cited

  • Research1

Source distribution

  • cloud.google.com1 (100%)