Question 1

涉及此次漏洞事件的 Claude 模型有哪些？

Accepted Answer

Anthropic said three models were implicated. They are Opus 4.7, Mythos 5, and an unreleased internal research test model. The activity spanned six evaluation runs, four of which hit the same organization.

Question 2

既然处于测试环境中，Claude 是如何接触到真实系统的？

Accepted Answer

A misconfiguration in evaluations run with Anthropic's partner Irregular left the test machines with live internet access. Anthropic's prompt had told Claude the environment was a simulation with no connectivity, so the models treated real systems as part of the exercise.

Question 3

这些攻击是否造成了现实世界的损害？

Accepted Answer

Yes. Mythos 5 published a malicious Python package to PyPI that stayed online for about an hour and was downloaded and run on 15 real systems. Opus 4.7 pulled credentials and reached a database of production data before Anthropic detected the activity.

METR

Anthropic放弃对METR安全报告的否决权

Anthropic称Claude在安全测试中入侵了三家公司

一份犀利简报。
每天。

METR

Anthropic放弃对METR安全报告的否决权

Anthropic称Claude在安全测试中入侵了三家公司

一份犀利简报。每天。

一份犀利简报。
每天。