Reported by 9 outlets

Timeline

1. original reporting

   Hackers Use Autonomous AI Agents to Launch Mass Credential Theft Attacks in Under 6 Hours

   cyberpress.org · 34d ago · September 9th, 2026

   Cybercriminals are increasingly using autonomous artificial intelligence agents to speed up cyberattacks and reduce the amount of manual work required from human operators. Google Threat Intelligence Group (GTIG) and Mandiant observed a suspected financially motivated threat actor compromise an organization’s cloud infrastructure and deploy a multi-agent attack framework. The attackers were able to plan, build, and execute a large credential-harvesting campaign in less than six hours. The campaign shows how threat actors are moving beyond basic AI prompts and beginning to use agentic AI systems that can independently perform several parts of an attack. Google said these systems can manage scanning operations, solve technical problems, make decisions, and continue working with limited human involvement. AI Agents Mass-Steal Credentials According to the report, the attackers used an AI coding chatbot together with prompts and preconfigured instructions written in Markdown files. These instructions acted like operational playbooks that told the AI agents how to perform different stages of the campaign. The autonomous framework scanned internet-facing systems for weaknesses and automatically attempted to harvest credentials. Bespoke Vulnerability Scanning and Credential Harvesting Campaign (Source: google) The agents were also capable of managing vulnerability-scanning pipelines, troubleshooting problems in real time, and rotating IP addresses without requiring an attacker to man

2. update from www.darkreading.com

   OpenAI agents wiki site targeted in Hugging Face attack

   www.darkreading.com · 34d ago · September 10th, 2026

   🖲️ # Cybersecurity # Ciberseguridad # Ciberseguranca # Security # Seguridad # Seguranca # News # Noticia # Noticias # Tecnologia # Technolog

   via Mastodon https://www.darkreading.com/cyberattacks-data-breaches/openai-agents-wiki-site-hugging-face-attack

3. update from aiguide.substack.com

   @ cigitalgem @ melaniemitchell Melanie Mitchell's explanation of the OpenAI / Hugging Face cybersecurity incident ( https:// aiguide.substac

   aiguide.substack.com · 32d ago · September 11th, 2026

   @ cigitalgem @ melaniemitchell Melanie Mitchell's explanation of the OpenAI / Hugging Face cybersecurity incident ( https:// aiguide.substac

   via Mastodon https://aiguide.substack.com/p/misleading-metaphors-and-real-risks

4. update from cyberpress.org

   Hackers Turn Claude AI Agents Into Autonomous Tools for Exploitation, Data Theft and Malware Evasion

   cyberpress.org · 32d ago · September 11th, 2026

   Threat actors are increasingly using Claude-based agentic workflows to automate reconnaissance, exploitation, credential theft, data exfiltration, and malware redevelopment. Anthropic said it disrupted operations in which attackers used AI not simply as a coding assistant, but as an orchestration layer capable of executing and iterating across much of the cyber kill chain. Anthropic’s investigation examined malicious activity disrupted between December 2025 and August 2026. Hackers Turn Claude AI Agents Into Autonomous Tools It identified suspected state-backed operators, financially motivated criminals, and hacktivists using Claude Haiku , Sonnet, and Opus models in autonomous or semi-autonomous attack frameworks. Attack lifecycle (Source: anthropic) Instead of manually asking a chatbot for individual code samples or technical advice, attackers built multi-agent frameworks able to conduct reconnaissance, identify exposed systems, test credentials, develop intrusion tooling, execute post-compromise tasks, and organize stolen data. Human operators typically remained responsible for target selection, campaign priorities, and reviewing the results, while AI agents handled repetitive technical tasks in parallel. Asset discovery, exploit development, phishing infrastructure setup, malware engineering, and bulk data processing tasks that previously required a team of specialists can increasingly be delegated to agents operating at machine speed. One of the report’s most serious cas

5. update from gbhackers.com

   Hackers Abuse Claude AI Agents to Automate Cyberattacks, Exploitation and Data Theft

   gbhackers.com · 32d ago · September 11th, 2026

   Anthropic reported disrupting multiple such operations between December 2025 and August 2026, involving groups suspected to be linked to […] The post Hackers Abuse Claude AI Agents to Automate Cyberattacks, Exploitation and Data Theft appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform .

6. update from bleepingcomputer.com

   Hackers abused Claude to extract secrets from 1.8M Android apps

   bleepingcomputer.com · 32d ago · September 11th, 2026

   Anthropic says multiple threat groups, including the financially motivated and state-sponsored espionage groups linked to Russia and China, tried to abuse its Claude AI model for malicious purposes. The AI company says that between December 2025 and August 2026, it recorded various forms of artificial intelligence misuse, including for cyber and influence operations, surveillance, scams, development of biological and conventional weapons, and model distillation. Over the eight-month period, Anthropic disrupted several activities linked to the ShinyHunters collective, infamous for massive data theft attacks that typically begin with social engineering and account compromise . An alleged French-speaking member of the group that used the handle ‘frkoo’ distributed a credential-harvesting pipeline across ten AWS EC2 workers that downloaded from multiple stores and then scanned for secrets in 1.8 million Android APKs. “This pipeline mass-downloaded 1.8 million distinct Android APKs from multiple app-store sources, decompiled them, and scanned for hardcoded secrets with TruffleHog,” Anthropic explains . “Verified findings were routed in real time to a Telegram group organized into over 100 source types.” The same actor used a separate automated process to collect GitHub organization email addresses and used them to obtain GitHub Personal Access Tokens (PATs). The two pipelines provided initial-access credentials that 'frkoo' used "for the bulk of the confirmed breaches" associated

7. update from www.theregister.com

   # Anthropic reveals fourth likely crime committed by its # AI https://www. theregister.com/ai-and-ml/2026 /09/10/anthropic-reveals-fourth-li

   www.theregister.com · 32d ago · September 11th, 2026

   Anthropic reveals fourth likely crime committed by its # AI https://www.

8. update from www.anthropic.com

   Hackers abused Claude to extract secrets from 1.8M Android apps Indicators extracted from public reporting. Source: https://www. anthropic.c

   www.anthropic.com · 32d ago · September 11th, 2026

   Hackers abused Claude to extract secrets from 1.8M Android apps Indicators extracted from public reporting.

9. update from www.bleepingcomputer.com

   Hackers abused Claude to extract secrets from 1.8M Android apps

   www.bleepingcomputer.com · 32d ago · September 11th, 2026

   Des chercheurs ont utilisé Claude (LLM d'Anthropic) pour analyser automatiquement 1,8 million d'apps Android et en extraire des secrets codé

   via Mastodon https://www.bleepingcomputer.com/news/security/hackers-abused-claude-to-extract-secrets-from-18m-android-apps/

10. mentioned by www.bleepingcomputer.com

    🤖 Anthropic: threat groups — incl. state-sponsored actors linked to Russia and China — abused Claude to automate exploitation and extract se

    www.bleepingcomputer.com · 31d ago · September 12th, 2026

11. update from cyberpress.org

    Threat Actors Use Claude AI Agents to Automate Cyberattacks, Exploitation and Data Theft

    cyberpress.org · 31d ago · September 12th, 2026

    Anthropic’s latest threat-intelligence findings show that the technology is being used not merely as a conversational assistant, but as an orchestration layer for multi-agent offensive workflows. In several cases, operators assigned broad objectives such as identifying vulnerable assets, gaining access, harvesting credentials, or collecting data and allowed AI agents to assess target environments, create scripts, execute commands, and iterate until the task was completed.

12. update from cyberworldops.eu

    Anthropic identified and blocked Claude accounts in Houthi-controlled northern Yemen used to support missile development and diagnose a fail

    cyberworldops.eu · 31d ago · September 12th, 2026

    Anthropic identified and blocked Claude accounts in Houthi-controlled northern Yemen used to support missile development and diagnose a fail

    via Mastodon https://cyberworldops.eu/en/claude-users-in-houthi-held-yemen-pursued-ai-assisted-missile

13. mentioned by gbhackers.com

    Threat Actors Use Claude AI Agents to Automate Cyberattacks and Steal Sensitive Data

    gbhackers.com · 31d ago · September 12th, 2026

14. update from gbhackers.com

    Claude AI agents used to automate cyberattacks and exfiltrate sensitive data. What changes here: it is no longer just prompts

    gbhackers.com · 31d ago · September 12th, 2026

    What changes here: it is no longer just prompts, it is autonomous agents executing multi-stage attacks.

15. update from arint.info

    RT @wccftech: A researcher buys 6TB of Anthropic Claude data dumps from a China-based LLM router and finds enough evidence of data leakage

    arint.info · 31d ago · September 12th, 2026

    RT @wccftech: A researcher buys 6TB of Anthropic Claude data dumps from a China-based LLM router and finds enough evidence of data leakage. The data was accessible through a third-party LLM routing service. via Mastodon https://arint.info/

16. update from www.anthropic.com

    "As models become increasingly capable, their risks will increase, unless # AI developers and society’s defenders act to make them safer." h

    www.anthropic.com · 31d ago · September 12th, 2026

    "As models become increasingly capable, their risks will increase, unless # AI developers and society’s defenders act to make them safer." h

    via Mastodon https://www.anthropic.com/threat-intelligence-report-september-2026

17. mentioned by www.bleepingcomputer.com

    "The AI company [Anthropic] says that between December 2025 and August 2026, it recorded various forms of artificial intelligence misuse, in

    www.bleepingcomputer.com · 30d ago · September 13th, 2026

18. update from www.bleepingcomputer.com

    Daar heb je weer zo'n AI kop die wat nuancering behoeft. Cybercriminelen gebruikten Claude om op grote schaal 1,8 miljoen Android apps te on

    www.bleepingcomputer.com · 29d ago · September 14th, 2026

    Daar heb je weer zo'n AI kop die wat nuancering behoeft.