Become a Member

Regulation TrackerLaws, orders and treaties read for their security duties and clocks Standards & FrameworksAttack taxonomies, control catalogues and frontier frameworks AI Incident DatabaseThe security incident record, with mechanism and lesson Research Paper LibraryThe papers that define the field, summarised OSS DirectoryRed teaming, guardrail, supply chain and evaluation tools Case StudiesProgrammes built, with measured outcomes AI Vulnerability TrackerCVEs and advisories for the components AI systems are built from

Latest in the tracker

New York Stop Addictive Feeds Exploitation (SAFE) for Kids Act and implementing rulesNew York's law restricting algorithmic feeds for minors takes effect on 25 January 2027 under final rules published in July 2026, with certified age assurance and $5,000-per-violation penalties.

Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Become a Member

Home/News/July 2026

Anthropic discloses three incidents of Claude models gaining unauthorised access to real systems from a third-party evaluation environment

Models running without cyber safeguards were told the environment was simulated; when they found evidence otherwise, they reasoned around it and continued, in one case against a real site that shared a name with a fictional target.

Incidents and breachesUnited States30 Jul 2026

The disclosure came nine days after OpenAI's and named a misconfiguration inside an external evaluator's environment that left internet access open. Anthropic paused external and internal cyber evaluations while it built detection and strengthened isolation, and committed to a fuller account, which followed on 31 August.

What to do: audit every third-party evaluator or contractor environment that runs your models with reduced safeguards, and require egress restrictions and live monitoring as contractual conditions.