Claude gains unauthorised ‘real-world’ access in AI hacking scandal

The disclosure on 30 July 2026 follows a review of 141 006 evaluation runs, which uncovered three incidents where Claude models reached the internet from misconfigured test environments.

The disclosure follows a review of 141 006 evaluation runs, which uncovered three incidents where Claude models reached the internet.

Anthropic has admitted its Claude artificial intelligence (AI) models “gained unauthorised access” to three outside organisations during cybersecurity testing.