AI agent systems

Incidents implicated systems

Incident 126334 Report
Chinese State-Linked Operator (GTG-1002) Reportedly Uses Claude Code for Autonomous Cyber Espionage

2025-11-13

Anthropic reportedly identified a cyber espionage campaign in which a purported Chinese state-linked group, designated GTG-1002 by Anthropic, allegedly jailbroke Claude Code and used it to automate 80–90% of multi-stage intrusions. The AI reportedly independently performed reconnaissance, vulnerability discovery, exploitation, credential harvesting, and data extraction across roughly 30 targets before the activity was detected and blocked.

Incident 162715 Report
Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

2026-07-30

During an Anthropic cybersecurity evaluation conducted with Irregular, Claude Opus 4.7 reportedly reached a real company whose domain matched a fictional target, extracted application and infrastructure credentials, and accessed a database containing several hundred rows of production data. Across four runs, the model continued attacking after recognizing that the target was likely real.

Incident 162815 Report
Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

2026-07-30

During an Anthropic cybersecurity evaluation with Irregular, Claude Mythos 5 reportedly created and published a malicious Python package to PyPI while pursuing a fictional target. The package was reportedly available for about an hour and ran on 15 real systems. On a security company's scanner, it reportedly exfiltrated credentials that Claude then used to access additional company infrastructure.

Incident 162915 Report
Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation

2026-07-30

During an Anthropic cybersecurity evaluation with Irregular, an internal research Claude model reportedly scanned roughly 9,000 internet targets after failing to reach its fictional target. It reportedly compromised a real company's Internet-facing application using credentials from an exposed debug page and SQL injection, then stopped after recognizing that the host was real.

AI agent systems

Incidents implicated systems

Incident 126334 ReportChinese State-Linked Operator (GTG-1002) Reportedly Uses Claude Code for Autonomous Cyber Espionage

Incident 162715 ReportClaude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Incident 162815 ReportClaude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

Incident 162915 ReportAnthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation

Related Entities Related EntitiesOther entities that are related to the same incident. For example, if the developer of an incident is this entity but the deployer is another entity, they are marked as related entities.

Related Entities

OpenAI

Incidents involved as both Developer and Deployer

Incidents Harmed By

Incidents involved as Developer

Users of Operator

Incidents Harmed By

Geoffrey A. Fowler

Incidents Harmed By

Operator

Incidents implicated systems

Instacart

Incidents implicated systems

GPT-4

Incidents implicated systems

Replit

Incidents involved as both Developer and Deployer

SaaStr

Incidents Harmed By

Jason Lemkin

Incidents Harmed By

end users of the SaaStr database

Incidents Harmed By

developers using Replit in production environments

Incidents Harmed By

vibe coding platform

Incidents implicated systems

Replit AI agent

Incidents implicated systems

Enterprise AI systems

Incidents implicated systems

LLM-integrated code assistants

Incidents implicated systems

Ransomware-as-a-service actors

Incidents involved as Deployer

North Korean IT operatives

Incidents involved as Deployer

Government of North Korea

Incidents involved as Deployer

Cybercriminals

Incidents involved as Deployer

Anthropic

Incidents involved as both Developer and Deployer

Incidents Harmed By

Incidents involved as Developer

Religious institutions

Incidents Harmed By

National security and intelligence stakeholders

Incidents Harmed By

Healthcare organizations

Incidents Harmed By

Government agencies

Incidents Harmed By

Incidents involved as Deployer

General public

Incidents Harmed By

Fortune 500 technology companies

Incidents Harmed By

Epistemic integrity

Incidents Harmed By

Emergency services

Incidents Harmed By

Consumers targeted by ransomware

Incidents Harmed By

LLM-enhanced ransomware toolkits

Incidents implicated systems

Claude Code

Incidents implicated systems

Claude

Incidents implicated systems

Unknown Chinese state-sponsored entity

Incidents involved as Deployer

State-linked operator using autonomous AI-enabled intrusion workflows

Incident 126334 Report
Chinese State-Linked Operator (GTG-1002) Reportedly Uses Claude Code for Autonomous Cyber Espionage

Incident 162715 Report
Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Incident 162815 Report
Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

Incident 162915 Report
Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation

Related Entities