HomeTagsSandboxing

sandboxing - Page 18

Stories from sandboxing come first, newest first, then stories from connected topics (Agent Sandbox, agent security, AI Agents, AI Agents, AI security, Cybersecurity), each labelled with where it comes from. This view is not indexed by search engines.

Latest

NVIDIA Launches OpenShell Agent Blueprint as ServiceNow Ships Arc

NVIDIA's OpenShell Reference Architecture aims to contain AI agents in software and silicon. ServiceNow's OpenShell-enforced Arc is now out.

Chrome Adds ‘Suspicious Site’ Warnings and ClickFix Checks for Scams

Google says Chrome's Enhanced Protection now flags suspicious sites, checks pages with a server-side Gemini model and spots copied ClickFix commands.

curl Now Takes Low and Medium Vulnerability Reports in Public

From 26 October, curl wants LOW and MEDIUM vulnerability reports filed publicly on GitHub, as maintainers face an avalanche of reports, many found with AI.

Army Cyber Documents Describe AI Agents That ‘Neutralise’ Targets

Documents describe ECHOTRIBBLE, a US Army Cyber Command project for AI agents that roam networks and "neutralise" targets. One firm was picked on 8 Oct.

Microsoft Says AI Agents Are Insider Risks, Adds Guardian Agents

Microsoft says frontier models "cannot be trusted", though not because they are malicious, and adds Guardian Agents to Project Perception to watch agents.

Hex-Rays Completes HexAI Deal to Add AI Agents for Security Research

CTech: Hex-Rays, maker of IDA Pro, is acquiring Israeli HexAI (ex-Ventris) for a reported $30m–$35m. Price unconfirmed; not said to have closed.

Epoch AI Says Open-Weight Models Trail Closed Ones on Cyber Skills by 6-7 Months

Epoch AI estimates open-weight models trail closed ones on cyber skills by 6-7 months, with Z.ai's GLM-5.3 on top, but its score rests on three results.

Microsoft and NVIDIA Publish an Open-Weight Model Risk Guide for Firms

Microsoft and NVIDIA's joint paper on open-weight model risk sets out five risk categories and argues openness alone does not decide risk. More to come.

NIST, NSA and CISA Set 10 Practices for Super Intelligence Incidents

NIST CAISSI, NSA's SISC and CISA set out ten voluntary practices for incidents where AI agents act outside instructions in training and testing.

Snyk Launches Evo Agentic AppSec, a Team of AI Security Agents

Snyk launched Evo Agentic AppSec. Most new agents are in preview; VulnBench and VulnBump figures are Snyk’s claims, not independent audits.

Latest on TSN

Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.