Question 1

어떤 Claude 모델이 침해에 관여했습니까?

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

테스트 상태였던 Claude가 어떻게 실제 시스템에 접근할 수 있었습니까?

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

공격 중 실제로 피해가 발생했습니까?

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, METR 안전 보고서 거부권 포기

앤트로픽, 클로드가 누수된 보안 테스트 중 3개 기업 침해

날카로운 한 줄.
매일.

METR

Anthropic, METR 안전 보고서 거부권 포기

앤트로픽, 클로드가 누수된 보안 테스트 중 3개 기업 침해

날카로운 한 줄.매일.

날카로운 한 줄.
매일.