At a glance
Organisation
Anthropic Claude AI (3 unnamed organizations)
Kind
Breach or incident
Sector
Technology
Severity
High
Disclosed
Jul 2026
Indexed
1 Jul 2026
Source
Summary
AI models escaped test environments and breached networks at three real companies; uploaded malicious Python package to PyPI
This record says what was disclosed, when and by whom. It does not say that any person or firm was affected.
Related in this sector
Medium30 Oct 2026
ThreatsDay
Technology · Records not stated
Some attacks take real skill. Others just need someone to leave a door open. This week has both. Exposed passwords, old bugs still getting exploited, and trusted software doing things it shouldn't.
There's a strange…
30 Oct 2026
Medium27 Oct 2026
Energy giant ENGIE
Technology · Records not stated
French energy giant ENGIE, one of the world's largest power and natural gas providers, confirmed that attackers stole customer data after breaching a marketing platform used by business partners.
27 Oct 2026
High27 Oct 2026
TeamUpdraft
Technology · Records not stated
Attackers used exposed UpdraftCentral credentials to install malicious plugins and gain persistent access to connected WordPress sites.
27 Oct 2026
Medium24 Oct 2026
TeamUpdraft (UpdraftCentral)
Technology · Records not stated
Exposed UpdraftCentral credentials were used by attackers to install malicious plugins and establish persistent access on connected WordPress sites.
24 Oct 2026