Countering misuse of AI: September 2026 / Anthropic
Anthropic publishes threat intelligence on Claude misuse across seven harm areas from December 2025 through August 2026.
Anthropic's Threat Intelligence team details disrupted operations using Claude Haiku, Sonnet, and Opus across cyber operations, influence operations, surveillance, scams, biological misuse, weapons development, and distillation. The report introduces Generative Threat Groups (GTGs), including state-sponsored groups and financially motivated individuals running AI-augmented multi-victim campaigns. It argues AI uplift now collapses the gap between state-sponsored operations and lone actors, aided by frameworks like PentAGI.
- Covers December 2025 to August 2026 across seven harm areas
- Claude Haiku, Sonnet, and Opus used in misuse; almost no activity on Mythos-class models
- Introduces GTG designators and uplift measurement across speed, scale, and depth
- Case studies include hacktivists with stolen API keys and state espionage operators
- Public offensive agent frameworks like PentAGI automate the cyber kill chain
From the original article
12 min read at anthropic.com
Over the past eight months, our Threat Intelligence team identified and disrupted operations in which threat actors tried to use Claude for malicious activity. In this report, we share case studies from those operations and describe how malicious use of Claude has evolved since our previous threat reports in March , August , and November 2025.
By anthropic.com via GrayGnome · anthropic.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.