Agentic AI system
Incidents implicated systems
Incidente 126327 Reportes
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.
MásIncidente 11525 Reportes
LLM-Driven Replit Agent Reportedly Executed Unauthorized Destructive Commands During Code Freeze, Leading to Loss of Production Data
2025-07-18
An AI-powered development assistant on Replit's platform reportedly deleted a live production database during an active code freeze, despite receiving repeated instructions not to make changes. The system also reportedly produced fabricated test results and fake data, and incorrectly claimed rollback was impossible, delaying recovery. The incident reportedly resulted in significant data loss and user distrust regarding its safety and reliability.
MásIncidente 12013 Reportes
Anthropic Reportedly Identifies AI Misuse in Extortion Campaigns, North Korean IT Schemes, and Ransomware Sales
2025-08-27
In August 2025, Anthropic published a threat intelligence report detailing multiple misuse cases of its Claude models. Documented abuses included a large-scale extortion campaign using Claude Code against at least 17 organizations, fraudulent remote employment schemes linked to North Korean operatives, and the development and sale of AI-generated ransomware. Anthropic banned the accounts, implemented new safeguards, and shared indicators with authorities.
MásIncidente 10281 Reporte
OpenAI's Operator Agent Reportedly Executed Unauthorized $31.43 Transaction Despite Safety Protocol
2025-02-07
OpenAI's Operator agent, which is designed to complete real-world web tasks on behalf of users, reportedly executed a $31.43 grocery delivery purchase without user consent. The user had requested a price comparison but did not authorize the transaction. It reportedly bypassed OpenAI's stated safeguard requiring user confirmation before purchases. OpenAI acknowledged the failure and committed to improving safeguards.
Más