AI

AI-Infra-Guard: Open-source security scanner for AI systems

AI, Don't miss, GitHub, Hot stuff, LLMs, News, open source, red team, scanner, software, Tencent /

AI-Infra-Guard: Open-source security scanner for AI systems 2026-09-09 at 10:13 By Mirko Zorz Tencent’s Zhuque Lab built AI-Infra-Guard, an open-source security scanner for AI systems. It fingerprints running services such as Ollama, vLLM and ComfyUI and checks them against more than 1,600 known CVEs, inspects MCP servers and agent skills across 14 categories of risk, […]

AI-Infra-Guard: Open-source security scanner for AI systems Read More »

Gartner: 70% of SOCs will pilot AI agents. Only 15% will see results

agentic AI, AI, cybersecurity, Don't miss, Expert analysis, Hot stuff, News, opinion, Prophet Security, SOC /

Gartner: 70% of SOCs will pilot AI agents. Only 15% will see results 2026-09-09 at 08:00 By Help Net Security In the Gartner report Validate the Promises of AI SOC Agents With These Key Questions, analysts Craig Lawson and Andrew Davies posit that “By 2028, 70% of large SOCs will pilot AI agents to augment […]

Gartner: 70% of SOCs will pilot AI agents. Only 15% will see results Read More »

What breach and attack simulation needs to become in the AI era

AI, cybersecurity, Don't miss, Expert analysis, Hot stuff, News, opinion, Picus Security, supply chain /

What breach and attack simulation needs to become in the AI era 2026-09-09 at 07:30 By Help Net Security Breach and attack simulation (BAS) has always had a supply chain. Somebody has to read the threat report, pull out the techniques, and turn them into something that will actually run against your controls. That somebody […]

What breach and attack simulation needs to become in the AI era Read More »

The Hidden Instructions That Can Hijack AI Agents

AI, Artificial Intelligence, Prompt Engineering /

The Hidden Instructions That Can Hijack AI Agents 2026-09-08 at 20:00 By Kevin Townsend Malicious prompts concealed in documents, metadata, emails, images and code can manipulate autonomous agents into taking dangerous actions. The post The Hidden Instructions That Can Hijack AI Agents appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original […]

The Hidden Instructions That Can Hijack AI Agents Read More »

Threat actors are giving AI agents a bigger role in cyberattacks

agentic AI, AI, cybercrime, Google, Mandiant, News /

Threat actors are giving AI agents a bigger role in cyberattacks 2026-09-08 at 17:55 By Sinisa Markovic AI agents are automating parts of cyberattacks with less human involvement, including vulnerability scanning, credential harvesting, and troubleshooting, according to Google Threat Intelligence Group’s Q3 2026 AI Threat Tracker. (Source: Google) The report draws on Mandiant incident response […]

Threat actors are giving AI agents a bigger role in cyberattacks Read More »

Product showcase: Doppler secures secrets for humans, pipelines, and AI agents

agentic AI, AI, credentials, News, Product showcase /

Product showcase: Doppler secures secrets for humans, pipelines, and AI agents 2026-09-08 at 08:00 By Help Net Security Every engineering team has spent years trying to keep credentials out of source code. Then AI agents moved the problem. Coding agents review code, agents run workflows, and MCP servers broker access to databases, cloud providers, and […]

Product showcase: Doppler secures secrets for humans, pipelines, and AI agents Read More »

Microsoft’s Project Zenith puts large AI models directly on developer PCs

agentic AI, AI, Microsoft, News, software development, Windows /

Microsoft’s Project Zenith puts large AI models directly on developer PCs 2026-09-08 at 07:30 By Anamarija Pogorelec Microsoft’s Project Zenith is a ready-to-code Windows 11 experience for developer-class PCs capable of running AI models with more than 30 billion parameters locally without relying on metered cloud tokens. Designed for systems with at least 64 GB […]

Microsoft’s Project Zenith puts large AI models directly on developer PCs Read More »

OpenAI Agents Hijack Another Victim Website

AI, Artificial Intelligence, attacks, Featured, OpenAI /

OpenAI Agents Hijack Another Victim Website 2026-09-07 at 15:03 By Kevin Townsend OpenAI agents made 15,000–18,000 autonomous edits to a German wiki over three months, evading moderation and echoing tactics seen in the Hugging Face breach. The post OpenAI Agents Hijack Another Victim Website appeared first on SecurityWeek. This article is an excerpt from SecurityWeek […]

OpenAI Agents Hijack Another Victim Website Read More »

OpenAI just hit a milestone on the road to self-improving AI

agentic AI, AI, cybersecurity, News, OpenAI, research /

OpenAI just hit a milestone on the road to self-improving AI 2026-09-07 at 12:05 By Anamarija Pogorelec OpenAI has announced that it has reached a goal set last fall of having an automated research intern by September 2026. The milestone means a system can carry out well-defined research tasks under human direction, including work that […]

OpenAI just hit a milestone on the road to self-improving AI Read More »

ToolHive: The open-source way to run any MCP server securely

AI, GitHub, News, open source, software /

ToolHive: The open-source way to run any MCP server securely 2026-09-07 at 08:30 By Anamarija Pogorelec ToolHive is an open-source platform that runs Model Context Protocol servers inside containers. An MCP server is the connector that lets an AI client like Cursor or Claude Code reach an outside tool, and Stacklok ships ToolHive under Apache […]

ToolHive: The open-source way to run any MCP server securely Read More »

Catch Raises $5 Million for AI Executive Assistant With Guardrails

AI, Artificial Intelligence, Cybersecurity Funding, funding /

Catch Raises $5 Million for AI Executive Assistant With Guardrails 2026-09-04 at 14:55 By Kevin Townsend Catch promises the capabilities of a trusted executive assistant, with built-in controls governing what data and systems it can access. The post Catch Raises $5 Million for AI Executive Assistant With Guardrails appeared first on SecurityWeek. This article is […]

Catch Raises $5 Million for AI Executive Assistant With Guardrails Read More »

A five-part inventory for your AI agent credentials

agentic AI, AI, automation, cybersecurity, how-to, News, strategy, tips, Video /

A five-part inventory for your AI agent credentials 2026-09-04 at 08:30 By Help Net Security In this Help Net Security video, Roy Katmor, co-founder and CEO of Orchid, explains why AI agents hold credentials that nobody reviews. Organizations build agents in AI studios, connect them to enterprise tools, and give them accounts to do useful […]

A five-part inventory for your AI agent credentials Read More »

OpenAI is putting $1 billion behind Daybreak for defenders working without enterprise budgets

AI, Don't miss, News, OpenAI /

OpenAI is putting $1 billion behind Daybreak for defenders working without enterprise budgets 2026-09-04 at 07:35 By Anamarija Pogorelec OpenAI committed $1 billion to subsidize access to its Daybreak cyber models, along with training and technical support, for organizations defending water and wastewater systems, the electric grid, state and local government, community and regional banks, […]

OpenAI is putting $1 billion behind Daybreak for defenders working without enterprise budgets Read More »

Most of the bugs Claude Mythos found have never been checked by a human

AI, cybersecurity, News, report, supply chain, vulnerability assessment /

Most of the bugs Claude Mythos found have never been checked by a human 2026-09-04 at 07:30 By Anamarija Pogorelec Anthropic pointed Claude Mythos Preview at 281 open-source projects and collected 23,019 candidate vulnerabilities. External security firms reviewed 1,900 of them. Maintainers received 1,596 reports and acknowledged 1,451; 97 fixes landed upstream, and 88 findings […]

Most of the bugs Claude Mythos found have never been checked by a human Read More »

Capsule Security Launches ‘AI Circuit Breaker’ to Stop Rogue Agents

AI, Artificial Intelligence, LLM /

Capsule Security Launches ‘AI Circuit Breaker’ to Stop Rogue Agents 2026-09-03 at 18:15 By Kevin Townsend New models, trained using NVIDIA Nemotron 3 Ultra, aim to catch rogue agent behavior before it executes, without the latency of large-model review. The post Capsule Security Launches ‘AI Circuit Breaker’ to Stop Rogue Agents appeared first on SecurityWeek. […]

Capsule Security Launches ‘AI Circuit Breaker’ to Stop Rogue Agents Read More »

Google’s Gemini 3.8 Flash takes on bigger AI models at a lower cost

AI, cybersecurity, Google, News /

Google’s Gemini 3.8 Flash takes on bigger AI models at a lower cost 2026-09-03 at 16:34 By Sinisa Markovic Google has introduced Gemini 3.8 Flash, available to developers today, and a gated sibling, Gemini 3.8 Flash Cyber, reserved for vetted security teams. “Our 3rd Flash release in just 6 wks,” Google CEO Sundar Pichai said […]

Google’s Gemini 3.8 Flash takes on bigger AI models at a lower cost Read More »

AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million

AI, Artificial Intelligence, Cybersecurity Funding, funding /

AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million 2026-09-03 at 15:00 By Kevin Townsend The startup’s firewall evaluates AI skills, plugins and MCP servers for malicious instructions, excessive permissions and software supply chain risks. The post AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million appeared first on […]

AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million Read More »

Researchers built a $7 gadget for anyone paranoid about hidden cameras in hotel rooms

AI, News, Privacy, research /

Researchers built a $7 gadget for anyone paranoid about hidden cameras in hotel rooms 2026-09-03 at 12:23 By Sinisa Markovic Most of us, staying in a hotel room or a vacation rental, have wondered at least once whether we’re safe there, whether someone might be watching or recording us without our knowledge. The thought alone […]

Researchers built a $7 gadget for anyone paranoid about hidden cameras in hotel rooms Read More »

Your AI agent’s system prompt is not a security control

agentic AI, AI, AWS, cybersecurity, News, report, SANS /

Your AI agent’s system prompt is not a security control 2026-09-03 at 10:53 By Anamarija Pogorelec An AI agent told in its system prompt to show a user only what that user is cleared to see will hand over more the moment someone talks it into doing so. Gee Rittenhouse, who oversees Security Hub, GuardDuty, […]

Your AI agent’s system prompt is not a security control Read More »

Scroll to Top