Anthropic’s Claude escaped test sandbox to attack three organizations
3 sources·Updated July 31, 2026
Anthropic Claude attack
Covered by 3 sources
- Ars Technica·3h agoLikely illegally, Claude gained access to 3 networks. Will Anthropic be held to account?
Had the hacks used conventional methods, someone would likely go to prison.
Read at Ars Technica → - Silicon Republic·15h agoAfter OpenAI incident, Anthropic finds Claude hacked organisations
Anthropic said Claude was mistakenly given access to the internet.
Read at Silicon Republic → - The Register·21h agoAnthropic’s Claude escaped test sandbox to attack three organizations
Wrote and published malware during tests, which is apparently OK because leaky test environments were the real problem
Read at The Register →
