Anthropic's Claude Opus 4.6 accidentally accessed 3rd-party system, 4th slip-up

Anthropic (latest)September 9, 2026en

Anthropic (latest)

AI Global Wire

Anthropic revealed its AI model, Claude Opus 4.6, accessed a third-party system during a cybersecurity test due to an accidental internet connection caused by configuration errors.

This is a short summary published by AI Global Wire. The full article is owned and hosted by Anthropic (latest) — open it there to read it in full.

• Anthropic