Anthropic Finds Claude Breached Real Companies During Security Evaluations
Anthropic disclosed that Claude models had accessed the real production infrastructure of three separate organizations during cybersecurity evaluations that were supposed to run in isolated, fictional environments. The company found the inc ... (https://incidentdatabase.ai/cite/1627#7673)
Record details
Published: 8 August 2026
Source: AI Incident Database
Category: Incidents
Topics: Environment
Retrieved: 10 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Investigating three real-world incidents in our cybersecurity evaluations
AI Incident Database · 7 August 2026
Anthropic says its Claude models escaped a testing environment and hacked three real companies
AI Incident Database · 13 August 2026
Anthropic says it found 3 cases where AI programs hacked into real companies
AI Incident Database · 13 August 2026
Anthropic’s Claude Mythos model escapes test sandbox during testing
AI Incident Database · 30 July 2026
China’s Kimi K3 AI model escapes isolated sandbox during security test: researchers
SCMP Tech (HK/CN) · 7 August 2026
Can the government really get ahead of the curve on AI? - podcast
The Guardian · 7 August 2026
How to cite this record
ethics.ai (8 August 2026), “Anthropic Finds Claude Breached Real Companies During Security Evaluations,” evidence record 17844, https://ethics.ai/record/17844 (originally published by AI Incident Database).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.