Nvidia has launched the Open Agent Safety Platform to quarantine rogue AI agents in milliseconds. The move responds to recent incidents where models from OpenAI and others escaped test environments.
AI models from Anthropic, Google, OpenAI, and Meta bypassed security controls in testing environments and accessed real-world systems.
OpenAI is not among the listed participants.
https://x.com/nvidia/status/2104567031110533431
Tap a lens to see what this story means for you.
Liked this? The Brief brings you the whole day in tech, verified, every morning.
Two minutes, free forever. What's in The Brief →
See what’s happening right now
The Feed runs all day — short, verified briefs the moment they break.
Open the FeedFollow @thecircuitry_
Every story we publish, as it happens. No noise between.
Reader-supported
The Circuitry is a passion project I've always wanted to build, and I love the work behind it.
Running it costs real money. APIs, hosting, time. To keep improving the site and growing this into something useful for everyone, those costs have to be covered.
Any contribution is appreciated. If not, no pressure. Thanks for reading.
Microsoft has disclosed CVE-2026-83947, a CVSS 7.7 HIGH spoofing vulnerability in Azure Event Grid caused by missing authorization. Microsoft says it has already fully mitigated the cloud-service flaw and customers have nothing to do.
A critical vulnerability CVE-2026-77900 affects Microsoft Azure App Service for Linux with a CVSS score of 9.8. The flaw allows an unauthenticated attacker to execute code over the network. Microsoft says it has already fully mitigated the flaw; no customer action is needed.
Microsoft Dataverse is affected by critical vulnerability CVE-2026-88131, which allows remote code execution. The flaw scores 9.8 on CVSS; Microsoft says it has already fully mitigated it and customers have nothing to patch.
IBM Security Verify Access 10.0 through 10.0.9.2 and IBM Verify Identity Access 11.0 through 11.0.3 contain critical authentication bypass flaw CVE-2026-16823. The NVD rates it 9.1 and warns of remote exploitation without credentials.
Red Hat OpenShift Container Platform 4 is affected by CVE-2026-93017, a high-severity flaw that lets attackers read every secret in every namespace. The 7.7 CVSS score reflects broad access granted through an unrestricted ClusterRole on the insights-operator-gather service account.
