Claude Used to Automate Exploitation and Data Theft Across Multiple Victims
-
Anthropic has issued a warning about the misuse of its Claude models by both cybercriminals and state-sponsored hackers, according to a report covering activity observed between December 2025 and August 2026. The company says these actors have leveraged Claude for a range of malicious purposes, including cyber attacks, weapons design, propaganda, and mass surveillance.
Anthropic refers to these adversaries as Generative Threat Groups (GTGs), a category that includes state-sponsored groups, financially motivated criminals, and commercial entities. The disclosed activity spans multiple victims, with the models used to automate exploitation and data theft.
- Threat actors involved: state-sponsored groups, financially motivated criminals, and commercial actors
- Observed period: December 2025 to August 2026
- Misuse categories cited: cyber attacks, weapons design, propaganda, and mass surveillance
The report does not specify particular vulnerabilities or CVE identifiers tied to these campaigns, so defenders should focus on broader detection and response rather than signature-based indicators alone.
Source: The Hacker News
Has your organization adjusted its threat model to account for AI-assisted exploitation and data theft?
Hello! It looks like you're interested in this conversation, but you don't have an account yet.
Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.
With your input, this post could be even better 💗
Register Login