agentic AI
GPT-Red beat human red teamers on a prompt injection test
GPT-Red is an automated red-teaming model that OpenAI trains to find prompt injection weaknesses. It works the way a human red-teamer does. It sends a prompt, watches how a …
SingGuard-NSFA: Open-source guardrails for agentic AI
SingGuard-NSFA is an open-source guardrail framework aimed at operational threats in agent workflows. Four models ship at 0.8B, 2B, 4B, and 9B parameters, all built on Qwen3.5 …
The MDR renewal question: What changes when AI can handle the alerts
For most of the past decade, the managed detection and response (MDR) decision was a simple one: teams that couldn’t staff a 24/7 SOC outsourced detection and response …
“Context bombs” can frustrate AI-driven attacks, researchers found
A new approach tried out by Tracebit researchers has proven very effective at stopping AI agents from fully compromising targeted environments. What makes it notable …
Cynative: Open-source deep research agent
Running a large language model against a live cloud account to hunt for security holes comes with an obvious hazard. An agent that holds real credentials and a mandate to poke …
A hardware security AI assistant that checks chips for hidden backdoors
Chip designers license blocks of circuitry from outside vendors and drop them into larger products. A single processor can carry components from a range of suppliers, each …
99.9% of fixable AI vulnerabilities remain unpatched
Organizations build, deploy, and operate AI in the cloud, but basic cybersecurity hygiene is often sacrificed for speed, according to Orca Security’s 2026 State of AI Security …
AWS gives its ERP agent deny-by-default rules and a separate identity
Accounts receivable teams at large companies spend hours each day matching incoming bank payments to invoices by hand. When those payments sit unmatched for days, cash flow …
Your coding agent says no in chat and yes in the code
Millions of developers share their keyboard with GitHub Copilot. Inside Visual Studio Code, it opens their files, writes and edits code, runs scripts, and reworks its own …
Malicious AI agent skills can slip past the scanners built to stop them
Developers who build with AI coding agents grab capabilities off public marketplaces the same way they grab packages from npm or PyPI. The add-ons are called agent skills. …
Thousands of malicious AI skills found capable of stealing data, running malware
AI agents can browse the web, use external tools, execute commands, and perform tasks on behalf of users. Many rely on skills that define how they interact with services and …
Claude Cowork turns your phone into a remote control for AI work
Anthropic started rolling out Claude Cowork, an AI agent that completes multi-step tasks, in beta for Max users on mobile and the web. They describe a goal, and Claude plans …