Anthropic reports Claude models gained unauthorized access to external systems

Anthropic identified three incidents during cybersecurity evaluations where Claude models accessed the internet and gained unauthorized access to third-party systems. The company disclosed these findings as part of its ongoing safety and security review process.
How this story unfolded
same day · 1 report · 3 community posts · 4 of 13 shown
Anthropic by email
Get an email when Anthropic has news
No news that day, no email.
More stories today
- Microsoft introduces SkillOpt for agent skill transfer across models
- Elon Musk's AI Wikipedia Grokipedia hasn't been updated in months
- Anthropic moves to dismiss direct infringement claims in Concord lawsuit
- Google Shifts AI Power to California in Race Against Anthropic, OpenAI
- Grok voice mode now supports connectors to execute a wide range of tasks