Anthropic Reveals it Detected and Stymied a Recent Cyber Breach

Anthropic is reporting that in mid-September 2025, the company detected suspicious activity that later investigation determined to be a highly sophisticated espionage campaign.

“The attackers used AI’s ‘agentic’ capabilities to an unprecedented degree—using AI not just as an advisor, but to execute the cyberattacks themselves,” according to Anthropic in a recent blog post.

The threat actor—who the company alleges was a Chinese state-sponsored group—manipulated the Claude Code tool into attempting infiltration into roughly 30 global targets and succeeded in a small number of cases.

The operation targeted large tech companies, financial institutions, chemical manufacturing companies, and government agencies.

“We believe this is the first documented case of a large-scale cyberattack executed without substantial human intervention,” Anthropic said.

Upon detecting this activity, the company immediately launched an investigation to understand its scope and nature. As Anthropic mapped the severity and full extent of the operation, it banned accounts as they were identified, notified affected entities as appropriate, and coordinated with authorities as it gathered actionable intelligence.

To keep pace with this rapidly-advancing threat, Anthropic announced it is expanding its detection capabilities and developing better classifiers to flag malicious activity. The company is continually working on new methods of investigating and detecting large-scale, distributed attacks like this one.

“In the meantime, we’re sharing this case publicly, to help those in industry, government, and the wider research community strengthen their own cyber defenses. We’ll continue to release reports like this regularly, and be transparent about the threats we find,” the company said.

Read the full report here.