Nvidia Open Agent Safety Platform launch adds OpenShell sandboxing and Sentry watchdog enforcement
Security Tool/Service
Summary
Hide ▲
Show ▼
Nvidia launched Open Agent Safety Platform, adding sandboxing, policy enforcement, and hardware-backed monitoring for AI agents that can drift outside intended boundaries. The release matters because it gives operators a concrete control stack for containing agent behavior from testing through deployment.
Related Happenings
OpenAI Astra reaches Critical cybersecurity threshold with Daybreak Blue tester access
Security Tool/Service
H score18
First: 02.09.2026 21:27
Last: 02.09.2026 21:27
Sources 1
About this happening:
OpenAI has moved Astra into a controlled tester-access phase after classifying it at the Critical cybersecurity capability threshold, raising the stakes for advanced AI-as...
OpenAI Astra reaches Critical cybersecurity threshold with Daybreak Blue tester access
Security Tool/ServiceAbout this happening: OpenAI has moved Astra into a controlled tester-access phase after classifying it at the Critical cybersecurity capability threshold, raising the stakes for advanced AI-as...
NVIDIA Ampere-class GPUs GPUThor Rowhammer ECC bypass privilege-escalation flaw
Vulnerability
H score26
First: 26.08.2026 21:48
Last: 26.08.2026 21:48
Sources 1
About this happening:
GPUThor is a Rowhammer vulnerability affecting NVIDIA workstation GPUs with GDDR6 memory that can defeat ECC and enable denial-of-service plus host root pr...
NVIDIA Ampere-class GPUs GPUThor Rowhammer ECC bypass privilege-escalation flaw
VulnerabilityAbout this happening: GPUThor is a Rowhammer vulnerability affecting NVIDIA workstation GPUs with GDDR6 memory that can defeat ECC and enable denial-of-service plus host root pr...
Obsidian Security adds native governance controls for Claude Code and Cowork
Security Tool/Service
H score19
First: 04.08.2026 15:00
Last: 04.08.2026 15:00
Sources 1
About this happening:
Obsidian Security expanded its agent governance platform with native controls for Claude Code and Cowork, tightening enterprise oversight of AI-agent access to production...
Obsidian Security adds native governance controls for Claude Code and Cowork
Security Tool/ServiceAbout this happening: Obsidian Security expanded its agent governance platform with native controls for Claude Code and Cowork, tightening enterprise oversight of AI-agent access to production...
ChatGPT Workspace Agents CSRF AgentForger security flaw
Vulnerability
H score40
First: 24.07.2026 14:53
Last: 24.07.2026 14:53
Sources 1
About this happening:
OpenAI's ChatGPT Workspace Agents faced a cross-site request forgery (CSRF) flaw that let a single phishing link create and deploy an attacker-controlled agent inside...
ChatGPT Workspace Agents CSRF AgentForger security flaw
VulnerabilityAbout this happening: OpenAI's ChatGPT Workspace Agents faced a cross-site request forgery (CSRF) flaw that let a single phishing link create and deploy an attacker-controlled agent inside...
LabubaRAT Rust RAT masquerading as NVIDIA software on Windows
Malware Activity
H score24
First: 14.07.2026 19:52
Last: 14.07.2026 19:52
Sources 1
About this happening:
A newly documented Rust-based RAT, LabubaRAT, now gives operators Windows host control with file movement, screenshot capture, and traffic proxying. The malware masq...
LabubaRAT Rust RAT masquerading as NVIDIA software on Windows
Malware ActivityAbout this happening: A newly documented Rust-based RAT, LabubaRAT, now gives operators Windows host control with file movement, screenshot capture, and traffic proxying. The malware masq...
Timeline
-
28.09.2026 13:27 2 articles · 2h ago
Nvidia launches Open Agent Safety Platform for AI agent containment
Initial DisclosureNvidia announced the Open Agent Safety Platform, combining the OpenShell open source runtime with Sentry on BlueField-4 DPUs to sandbox agents, enforce policy, and monitor behavior outside the host. The release says OpenShell is broadly available at version 0.1.0 and that Sentry can quarantine agents that move outside their software boundary.
Show sources
- Nvidia Unveils AI Agent Safety Platform With Hardware-Based Watchdog — www.securityweek.com — 28.09.2026 13:27
- Nvidia Unveils AI Agent Safety Platform With Hardware-Based Watchdog — www.securityweek.com — 28.09.2026 13:27