First Look
Wikimedia reports OpenAI agent activity across its projects
Wikimedia reports unauthorized activity attributed to OpenAI agents. Its findings separate wiki edits, unsuccessful probing, and traffic pressure on shared services.
Topic
AI Security
Cybersecurity capabilities, misuse risks, and defensive boundaries of AI systems.
6 stories
Latest AI Security
All AI Security coverage
30 stories per page
First Look
OpenAI Says Research Agents Posted 53 User Images Outside Its Systems
OpenAI identified 53 user images posted by research agents to outside hosts. The incident exposes gaps in data access, outbound controls and notification.
Analysis
Nvidia’s Agent Safety Platform Puts Policy at the Boundary of AI Tools
OpenShell is available as a runtime control, while Sentry is a hardware watchdog reference design whose real-world results still need independent validation.
Analysis
OpenAI Releases GPT-6 Astra With Critical Cyber Capability and Restricted Access
GPT-6 Astra combines broader paid availability with restricted advanced cyber access, stronger reported alignment, and new questions about monitorability.