agentic AI

Hidden instructions in README files can make AI agents leak data

agentic AI, Artificial Intelligence, cybersecurity, News, research /

Hidden instructions in README files can make AI agents leak data 2026-03-17 at 08:02 By Sinisa Markovic Developers rely on AI coding agents to set up projects, install dependencies, and run commands by following instructions in repository README files, which provide setup guidance for software projects. New research identifies a security risk when attackers hide […]

Hidden instructions in README files can make AI agents leak data Read More »

AI coding agents keep repeating decade-old security mistakes

agentic AI, Anthropic, Artificial Intelligence, Claude Code, cybersecurity, Don't miss, DryRun Security, Google, Hot stuff, News, OpenAI, programming, report /

AI coding agents keep repeating decade-old security mistakes 2026-03-13 at 08:01 By Anamarija Pogorelec Coding agents are now writing production features on real development teams, and a new report from DryRun Security shows that those agents introduce security vulnerabilities at a high rate across nearly every type of application they build. “AI coding agents can […]

AI coding agents keep repeating decade-old security mistakes Read More »

Agentic attack chains advance as infostealers flood criminal markets

agentic AI, Artificial Intelligence, attacks, CISO, cyber risk, Don't miss, Flashpoint, News, report, survey, Threat Intelligence, threats /

Agentic attack chains advance as infostealers flood criminal markets 2026-03-12 at 08:35 By Mirko Zorz Cybercriminals spent much of 2025 automating their operations, shifting from one-off attacks to systems that can run entire intrusion cycles with minimal human input. Data collected from criminal forums, illicit marketplaces, and underground chat services shows a threat environment where […]

Agentic attack chains advance as infostealers flood criminal markets Read More »

Open-source tool Sage puts a security layer between AI agents and the OS

agentic AI, cybersecurity, Don't miss, Gen Digital, GitHub, Hot stuff, News, open source, software /

Open-source tool Sage puts a security layer between AI agents and the OS 2026-03-09 at 08:06 By Anamarija Pogorelec Autonomous AI agents running on developer workstations execute shell commands, fetch URLs, and write files with little or no inspection of what they are doing. Open-source project Sage inserts an interception layer between an AI agent […]

Open-source tool Sage puts a security layer between AI agents and the OS Read More »

Cursor Automations turns code review and ops into background tasks

agentic AI, Artificial Intelligence, automation, Cursor, News /

Cursor Automations turns code review and ops into background tasks 2026-03-06 at 12:18 By Anamarija Pogorelec Cursor Automations, the always-on agent platform from Cursor, is expanding with a new generation of autonomous systems that streamline code review, incident response, and other engineering workflows. The platform runs AI agents on schedules or in response to development […]

Cursor Automations turns code review and ops into background tasks Read More »

As AI agents start making purchases, security teams must rethink risk

agentic AI, Chargebacks911, Don't miss, enterprise, Features, fraud, Hot stuff, News, Privacy, procurement, risk /

As AI agents start making purchases, security teams must rethink risk 2026-03-05 at 08:17 By Zeljka Zorz In this Help Net Security interview, Donald Kossmann, CTO at fintech company Chargebacks911, talks about the emerging security, fraud, and governance risks of “agentic commerce,” where AI agents can autonomously make purchasing decisions on behalf of users or […]

As AI agents start making purchases, security teams must rethink risk Read More »

Engineering trust: A security blueprint for autonomous AI agents

agentic AI, Artificial Intelligence, cybersecurity, Don't miss, framework, Google, Hot stuff, LLMs, News, opinion /

Engineering trust: A security blueprint for autonomous AI agents 2026-03-05 at 07:06 By Help Net Security AI agents have evolved from just chatbots, answering questions to executing actions using various integrated tools, often autonomously, and as such the traditional security models have become less efficient. I have seen that firsthand as a security lead for […]

Engineering trust: A security blueprint for autonomous AI agents Read More »

The vulnerability that turns your AI agent against you

agentic AI, Comet, News, Perplexity, vulnerability, Zenity /

The vulnerability that turns your AI agent against you 2026-03-04 at 16:08 By Help Net Security Zenity Labs disclosed PleaseFix, a family of critical vulnerabilities affecting agentic browsers, including Perplexity Comet, that allow attackers to hijack AI agents, access local files, and steal credentials within authenticated user sessions. The vulnerabilities can be triggered through malicious […]

The vulnerability that turns your AI agent against you Read More »

AI went from assistant to autonomous actor and security never caught up

1Password, agentic AI, Artificial Intelligence, CISO, Databricks, Don't miss, Elastic, enterprise, Features, Hot stuff, MIT, News /

AI went from assistant to autonomous actor and security never caught up 2026-03-03 at 08:35 By Mirko Zorz Enterprise AI deployments have shifted from pilot programs to production systems handling customer data, executing business transactions, and integrating with core infrastructure. That has exposed a significant gap between what AI agents can do and what security […]

AI went from assistant to autonomous actor and security never caught up Read More »

AI risk moves into the security budget spotlight

agentic AI, Artificial Intelligence, cybersecurity, News, report, Thales, threats /

AI risk moves into the security budget spotlight 2026-03-02 at 09:08 By Anamarija Pogorelec Enterprises are pushing AI deeper into workflows that touch sensitive data across cloud platforms and SaaS apps. The 2026 Thales Data Threat Report, based on a survey of 3,120 respondents in 20 countries, places that shift alongside growing pressure on data […]

AI risk moves into the security budget spotlight Read More »

When cyber threats start thinking for themselves

agentic AI, Artificial Intelligence, Don't miss, News, opinion, SimSpace, tips, Video /

When cyber threats start thinking for themselves 2026-03-02 at 07:30 By Help Net Security In this Help Net Security video, Jason Rivera, Field CISO & Head of Solution Engineering at SimSpace, discusses how autonomous AI agents are changing cyber threats. Drawing on experience in the US Army, NSA, Deloitte, and CrowdStrike, he describes how security […]

When cyber threats start thinking for themselves Read More »

IronCurtain: An open-source, safeguard layer for autonomous AI assistants

agentic AI, Artificial Intelligence, Don't miss, GitHub, Hot stuff, News, open source /

IronCurtain: An open-source, safeguard layer for autonomous AI assistants 2026-02-28 at 07:07 By Zeljka Zorz Veteran security engineer Niels Provos is working on a new technical approach designed to stop autonomous AI agents from taking actions you haven’t specifically authorized. His open-source software solution, called IronCurtain, aims to neutralize the risk of an LLM-powered agent […]

IronCurtain: An open-source, safeguard layer for autonomous AI assistants Read More »

The $19.5 million insider risk problem

agentic AI, Artificial Intelligence, CISO, cyber risk, cybersecurity, Don't miss, Dtex Systems, Insider Threat, News, Ponemon Institute, report, Risk Management, survey /

The $19.5 million insider risk problem 2026-02-26 at 09:09 By Mirko Zorz Routine employee activity across corporate systems carries an average annual cost of $19.5 million per organization. That figure comes from the 2026 Cost of Insider Risks Global Report, conducted by the Ponemon Institute and based on data from 354 organizations that experienced one […]

The $19.5 million insider risk problem Read More »

Windows 365 for Agents brings managed cloud PCs to autonomous workflows

agentic AI, Artificial Intelligence, Microsoft, News, Windows /

Windows 365 for Agents brings managed cloud PCs to autonomous workflows 2026-02-24 at 13:02 By Anamarija Pogorelec Microsoft’s Windows 365 for Agents is a cloud platform that gives AI agents secure access to cloud PCs. It lets builders run copilots, agents, and automated workflows in Windows environments without managing infrastructure. The platform includes security, policy […]

Windows 365 for Agents brings managed cloud PCs to autonomous workflows Read More »

AI agents behave like users, but don’t follow the same rules

access controls, agentic AI, Artificial Intelligence, Cloud Security Alliance, cybersecurity, identity management, News, report /

AI agents behave like users, but don’t follow the same rules 2026-02-09 at 08:19 By Anamarija Pogorelec Security and governance approaches to autonomous AI agents rely on static credentials, inconsistent controls, and limited visibility. Securing these agents requires the same rigor and traceability applied to human users, according to Cloud Security Alliance’s Securing Autonomous AI […]

AI agents behave like users, but don’t follow the same rules Read More »

OpenAI Frontier organizes AI agents under one system

agentic AI, News, OpenAI, Oracle /

OpenAI Frontier organizes AI agents under one system 2026-02-05 at 17:20 By Sinisa Markovic OpenAI introduced Frontier, a platform designed to organize AI agents that perform business tasks within internal systems and workflows. The platform connects data from multiple internal systems including customer relationship management tools, ticketing platforms, and data warehouses. This integration creates a […]

OpenAI Frontier organizes AI agents under one system Read More »

n8n adds Chat Hub to centralize AI access inside automation workflows

agentic AI, automation, n8n, News /

n8n adds Chat Hub to centralize AI access inside automation workflows 2026-01-28 at 12:32 By Anamarija Pogorelec Teams using automation platforms are starting to treat conversational AI as another operational interface. That change is reflected in a new feature from n8n, which has introduced a built-in Chat Hub designed to let users interact with AI […]

n8n adds Chat Hub to centralize AI access inside automation workflows Read More »

More employees get AI tools, fewer rely on them at work

agentic AI, Artificial Intelligence, Deloitte, Don't miss, Kovant, News, report /

More employees get AI tools, fewer rely on them at work 2026-01-23 at 08:03 By Mirko Zorz People across many organizations now have access to AI tools, and usage keeps spreading. Some groups rely on AI during regular work, others treat it as an occasional helper. That gap between access and routine use sits at […]

More employees get AI tools, fewer rely on them at work Read More »

Agentic AI edges closer to everyday production use

agentic AI, Artificial Intelligence, Dynatrace, News, report /

Agentic AI edges closer to everyday production use 2026-01-23 at 07:31 By Anamarija Pogorelec Many security and operations teams now spend less time asking whether agentic AI belongs in production and more time working out how to run it safely at scale. A new Dynatrace research report looks at how large organizations are moving agentic […]

Agentic AI edges closer to everyday production use Read More »

New intelligence is moving faster than enterprise controls

agentic AI, Artificial Intelligence, cybersecurity, Data Protection, News, NTT, report /

New intelligence is moving faster than enterprise controls 2026-01-16 at 08:02 By Anamarija Pogorelec AI is being integrated into core enterprise systems faster than many organizations can secure and govern it. A new global study from NTT shows companies expanding AI deployment while gaps in infrastructure readiness, data integrity controls, and governance frameworks continue to […]

New intelligence is moving faster than enterprise controls Read More »

Scroll to Top