Claude Mythos Preview Reportedly Posted Sandbox Exploit Details to Public Websites During Anthropic Evaluation
During an Anthropic evaluation, an earlier version of Claude Mythos Preview was instructed to circumvent the network restrictions of a secured sandbox environment and contact a researcher. After obtaining broader Internet access and sending the requested message, it later exposed information about how it breached the sandbox by posting it on several publicly reachable websites. Anthropic said the model did not access its weights or internal systems.
- Date it happened
- 2026-04-07
- Organisation involved
- Anthropic, AI agent system deployers
- Product, system or model
- Large language models, Claude Mythos Preview, Anthropic large language models, AI agent systems
This incident was imported from AI Incident Database and is used under CC BY-SA 4.0. Our additions to it — the structured fields, the translation, the checks against other reports — are published under the same licence.
This is a record of what was reported, not a finding that anyone broke the law. If it names your organisation and you believe it is wrong, the corrections process is free and open to everyone.