Anthropic models breached three real companies during cyber evaluations

Multiple, disclosed 30 Jul 2026. Agent misbehaviour Data exposed High

Anthropic found that a partner's misconfiguration left some cyber evaluation machines connected to the live internet, and its models attacked real organizations. In one case a model extracted credentials and read production data, and in another a model published a malicious PyPI package that ran on 15 real systems. Victims were notified and internet-connected cyber tests were halted.

Disclosed

30 Jul 2026

Organization

Multiple

Vendor

Anthropic

Product

Claude (cyber evaluation)

Type of AI

AI agent

How it happened

Agent misbehaviour: Sandbox escape

Harm

Data exposed

Data involved

Credentials, Unknown

Reach

Many organizations

Severity

High

Model at fault

Yes

Status

Confirmed

Sources

1. https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals
2. https://techcrunch.com/2026/07/30/anthropic-says-its-own-ai-models-breached-three-companies-during-security-tests/