agentic AI

A $1,400 experiment in AI security auditing outperformed OpenAI’s Codex Security

agentic AI, AI, auditing, cybersecurity, Don't miss, Features, Hot stuff, News, open source, research /

A $1,400 experiment in AI security auditing outperformed OpenAI’s Codex Security 2026-06-23 at 08:30 By Mirko Zorz A research team has built a system that teaches AI agents to hunt for software bugs by writing the audit method down as plain text. The system, called EVOHUNT, keeps the underlying AI model fixed and improves only […]

A $1,400 experiment in AI security auditing outperformed OpenAI’s Codex Security Read More »

Only 7% of companies are ready for the AI agents they deployed

agentic AI, cyber risk, data, News, report, Veeam Software /

Only 7% of companies are ready for the AI agents they deployed 2026-06-23 at 07:00 By Anamarija Pogorelec Most organizations now run or pilot AI agents that operate on company data with limited human direction at each step, a share that reaches 88% in Veeam Software’s Data and AI Trust Gap report. The systems that

Only 7% of companies are ready for the AI agents they deployed Read More »

23 ClawHub plugins squatting official scopes expose AI registry security gaps

agentic AI, AI, cybersecurity, Don't miss, News, OpenClaw, research, Video /

23 ClawHub plugins squatting official scopes expose AI registry security gaps 2026-06-22 at 11:00 By Help Net Security Plugin registries for AI agents use npm-style scopes like @openclaw/ and @clawhub/ to signal who published a package. But on ClawHub, a registry whose plugins run with Claude, OpenClaw, and other agents, those official scopes weren’t reserved

23 ClawHub plugins squatting official scopes expose AI registry security gaps Read More »

Agent Beacon: Open-source telemetry layer for AI agents

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

Agent Beacon: Open-source telemetry layer for AI agents 2026-06-22 at 08:30 By Mirko Zorz AI coding agents such as Claude Code, Codex CLI, Cursor, and Claude Cowork run on developer laptops, CI jobs, cloud environments, where they edit files, run commands, and call outside tools. Beacon, an open-source project from Asymptote Labs, configures telemetry for

Agent Beacon: Open-source telemetry layer for AI agents Read More »

What happens to oversight when AI agents write a lab’s own code

agentic AI, AI, cybersecurity, Don't miss, News, research /

What happens to oversight when AI agents write a lab’s own code 2026-06-18 at 08:00 By Mirko Zorz Inside the labs building frontier AI, a growing share of the coding gets done by the AI itself. These agents write, edit, and run software with light human oversight between steps, and they reach into production infrastructure,

What happens to oversight when AI agents write a lab’s own code Read More »

Low-skilled attacker used Claude, Codex to breach 14 companies

agentic AI, attack, attack tools, Claude Code, cybersecurity, Don't miss, Hot stuff, LLMs, News, research /

Low-skilled attacker used Claude, Codex to breach 14 companies 2026-06-17 at 18:43 By Zeljka Zorz Researchers have long warned that AI agents could lower the skill floor for offensive cyber operations, and a recent report by OALABS (Open Analysis) researchers bears that out. After recovering and analyzing over 1,000 agent sessions from a compromised server

Low-skilled attacker used Claude, Codex to breach 14 companies Read More »

The SOC’s visibility gap comes down to staffing

agentic AI, AI, cybersecurity, Don't miss, LLMs, News, SANS, security operations, SOC, survey, Threat Intelligence /

The SOC’s visibility gap comes down to staffing 2026-06-17 at 09:00 By Mirko Zorz AI has settled into security operations centers faster than any earlier wave of technology. Around four in five practitioners report reaching for AI or machine learning tools in their daily work. The catch shows up one layer down. Roughly a third

The SOC’s visibility gap comes down to staffing Read More »

How to use NIST and ISO frameworks to govern AI agents

agentic AI, CISO, cybersecurity, Don't miss, Expert analysis, Expert corner, framework, Hot stuff, News, NIST, opinion, Token Security /

How to use NIST and ISO frameworks to govern AI agents 2026-06-12 at 11:07 By Help Net Security Security leaders no longer need convincing that AI agents introduce risk. What’s missing is how to govern them once they move into production and begin operating autonomously across enterprise environments. AI agents already read sensitive documents, invoke

How to use NIST and ISO frameworks to govern AI agents Read More »

Prompt injection still drives most agentic AI security failures in production

agentic AI, AI, cybersecurity, Don't miss, News, OWASP, report, threats /

Prompt injection still drives most agentic AI security failures in production 2026-06-11 at 08:43 By Anamarija Pogorelec A backdoor sat on PyPI for three hours in March 2026. Nearly 47,000 downloads occurred during the window. The compromised package, LiteLLM, serves as the language-model gateway for CrewAI, DSPy, Microsoft GraphRAG, and dozens of other AI agent

Prompt injection still drives most agentic AI security failures in production Read More »

Organizations can’t see much of their mobile AI activity

agentic AI, AI, BYOD, Compliance, cybersecurity, Lookout, mobile security, News, report, smartphones /

Organizations can’t see much of their mobile AI activity 2026-06-11 at 08:43 By Anamarija Pogorelec Organizations have limited visibility into AI activity on mobile devices despite security leaders expressing confidence in their AI governance, according to Lookout’s “Solving for the Mobile AI Blind Spot: Executive Confidence Meets Technical Reality” report. Mobile AI visibility gaps Enterprises

Organizations can’t see much of their mobile AI activity Read More »

Apple Intelligence can now replace weak passwords without user intervention

agentic AI, apple, authentication, cybersecurity, iOS, iPad, iPhone, macOS, News, password management, Privacy /

Apple Intelligence can now replace weak passwords without user intervention 2026-06-09 at 15:21 By Anamarija Pogorelec Apple’s next generation of Apple Intelligence, the company’s personal intelligence system, expands its capabilities and introduces new security features in Passwords. Automatically Fix Passwords (Source: Apple) Introduced as a standalone app in 2024, Passwords gives users a central place

Apple Intelligence can now replace weak passwords without user intervention Read More »

Treating AI agents like service accounts for federated query security

access control, agentic AI, AI, CISO, cybersecurity, Don't miss, Features, LLMs, News, opinion, strategy /

Treating AI agents like service accounts for federated query security 2026-06-09 at 08:46 By Mirko Zorz In this interview with Help Net Security, Paras Malhotra, CISO at Starburst, explains how the company handles data governance across federated query environments. Topics include layering Starburst’s access controls above native source permissions, tiering vendor risk across more than

Treating AI agents like service accounts for federated query security Read More »

GitHub Copilot app launches as desktop home for AI coding agents

agentic AI, code, GitHub, News, software /

GitHub Copilot app launches as desktop home for AI coding agents 2026-06-08 at 07:15 By Sinisa Markovic GitHub introduced the Copilot app, a desktop application built for working with AI coding agents, at Microsoft Build 2026. The release expands GitHub’s Copilot product line beyond editor integrations and command-line tools into a dedicated workspace for directing

GitHub Copilot app launches as desktop home for AI coding agents Read More »

AgentGG: Open-source agentic SAST scanner

agentic AI, Don't miss, GitHub, Hot stuff, News, open source, software, TikTok /

AgentGG: Open-source agentic SAST scanner 2026-06-05 at 09:24 By Mirko Zorz Static analysis tools have spent years matching source code against known-bad patterns and handing engineers long lists of candidate issues to triage by hand. AgentGG approaches the same job with AI agents that read the code, follow imports, walk the call graph, and confirm

AgentGG: Open-source agentic SAST scanner Read More »

AI agent governance gets harder when agents outnumber your people

agentic AI, CISO, cybersecurity, enterprise, News, opinion, strategy, tips, Video /

AI agent governance gets harder when agents outnumber your people 2026-06-05 at 09:24 By Help Net Security In this Help Net Security video, Amit Gautam, CTO at Abluva, explains the security risks that autonomous AI agents bring into enterprise environments. He opens with a real case: a reconciliation agent at a financial services firm had

AI agent governance gets harder when agents outnumber your people Read More »

Security of 100 AI Agents Tested and Ranked – What You Need to Know

agentic AI, AI, Artificial Intelligence, Data Protection /

Security of 100 AI Agents Tested and Ranked – What You Need to Know 2026-06-03 at 20:19 By Kevin Townsend The AI Risk Quadrant evaluates AI agents based on three factors: how vulnerable they are to compromise, the potential impact of a breach, and the strength of their security defenses. The post Security of 100

Security of 100 AI Agents Tested and Ranked – What You Need to Know Read More »

Only 11% of production agents pass the AI agent security bar

agentic AI, AI, cyber risk, cybersecurity, Don't miss, enterprise, Features, Hot stuff, News, research, security controls /

Only 11% of production agents pass the AI agent security bar 2026-06-03 at 14:00 By Mirko Zorz Enterprise teams are running AI agents that write code, drive browsers, answer customer calls, manage cloud infrastructure, and query data warehouses with standing credentials. A new independent assessment of 100 production agents finds that nearly all of them

Only 11% of production agents pass the AI agent security bar Read More »

Microsoft Scout agent opens a new category of always-on Autopilots

access control, agentic AI, AI, automation, data, Microsoft, News /

Microsoft Scout agent opens a new category of always-on Autopilots 2026-06-03 at 11:28 By Anamarija Pogorelec Workplace AI assistants have mostly waited for a prompt before doing anything. A user asks, the tool answers, and the exchange ends there. Microsoft is putting a different kind of agent inside its Office applications, one designed to keep

Microsoft Scout agent opens a new category of always-on Autopilots Read More »

NVIDIA goes open source with a big batch of physical AI agent tools

agentic AI, Don't miss, industrial robots, News, NVIDIA, open source /

NVIDIA goes open source with a big batch of physical AI agent tools 2026-06-01 at 11:46 By Anamarija Pogorelec NVIDIA just dropped a big batch of open-source “physical AI” skills and tools, and they’re designed to make a roboticist’s life a whole lot easier. The idea? Take the messy, complicated work behind robots, self-driving cars,

NVIDIA goes open source with a big batch of physical AI agent tools Read More »

OWASP Agent Memory Guard: Stop AI agents from being weaponized through their own memory

agentic AI, Don't miss, GitHub, News, open source, OWASP, software /

OWASP Agent Memory Guard: Stop AI agents from being weaponized through their own memory 2026-06-01 at 08:19 By Mirko Zorz AI agents keep memory across sessions. Conversation history, vector stores, scratchpads, and RAG indexes persist between runs, and anything written into that store becomes a privileged input the agent reads back later. An attacker who

OWASP Agent Memory Guard: Stop AI agents from being weaponized through their own memory Read More »

Scroll to Top