Evidence record 15500 · automatically gathered

Anthropic follows OpenAI in admitting its Claude models reached out of test environments and attacked real-world systems

Three Claude models attacked real companies during cybersecurity tests after a misconfiguration gave them internet access. One published malware on PyPI that infected 15 systems. Another kept attacking after recognizing its target was real. Anthropic calls it an operational error. The article Anthropic follows OpenAI in admitting its Claude models reached out of test environments and attacked real-world systems appeared first on The Decoder .

Record details

Published: 31 July 2026
Source: The Decoder
Category: News
Topics: Environment
Retrieved: 1 August 2026

source-onlyevidence status

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.

How to cite this record

ethics.ai (31 July 2026), “Anthropic follows OpenAI in admitting its Claude models reached out of test environments and attacked real-world systems,” evidence record 15500, https://ethics.ai/record/15500 (originally published by The Decoder).

JSON

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.