2026-10-20 11:30 UTC
Security Journalism
Security Week · Eduard Kovacs · indexed 2026-10-20 11:35 UTC
Microsoft says companies should treat AI agents as insiders, and is adding controls that grant access per task and tighten it as an agent’s risk rises. The post Microsoft Targets Rogue AI Agents With Dynamic Permissions, Risk Scoring appeared first on SecurityWeek.
P0
2026-10-20 07:44 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-20 08:35 UTC
Microsoft urges organizations to secure AI Agents as insider threats, using dynamic permissions, continuous risk monitoring and automated containment. Microsoft published a detailed blog post explaining how organizations should secure AI agents. Microsoft sees them as a growing insider threat, not just a possible risk in the future. AI agents are not dangerous by nature, […]
P0
2026-10-19 16:34 UTC
Vendor Research
Rapid7 · Shriram Munde · indexed 2026-11-17 14:55 UTC
Why the controls on an AI agent have to live outside of it, and what a security operations team can do to implement and maintain those controls.The new privileged user in your environmentSecurity teams spent two decades learning how to work with the people they trust most. Domain admins, DBAs, finance approvers and contractors with VPN access all get a mature playbook: verified identity, scoped access, logged activity and a fast way to revoke it all.Today, we’re navigating the same kind of acce…
P15
2026-10-19 14:14 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-19 14:55 UTC
The worst problems don't always come with a warning. Sometimes they arrive through a service everyone trusts, a device someone bought, or a system nobody thought to check. By the time something looks wrong, the damage may already be done. This week had plenty of that. Trusted connections became a problem. Hardware wasn't as safe as it looked. Old bugs found new victims, and some systems were
P25
2026-10-19 13:17 UTC
Vendor Research
Tenable Blog · Clément Notin · indexed 2026-10-19 13:30 UTC
Discover how to secure AI agents in your cloud environment with Tenable One Cloud Exposure. We explore Microsoft Entra Agent ID and provide essential best practices for robust agentic AI identity security.Key takeawaysUnderstand your current maturity level and then build an appropriate action plan to secure your agent identities.Use your cloud providers’ native tools or Tenable One Cloud Exposure to locate and catalog every AI agent operating in your environment.Do not assign human identities o…
P0
2026-10-19 10:06 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-19 11:50 UTC
A fake Web3 accelerator has been observed pushing information stealers and backdoors to Windows and macOS systems using malicious npm packages under the pretext of offering free artificial intelligence (AI) credits for Anthropic Claude and Google Gemini, coding tools, and security audits. "The tools delivered information-stealing malware and backdoors for macOS and Windows machines," Elastic
P0
2026-10-18 13:46 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-18 14:30 UTC
Security Affairs AI-CYBERSECURITY newsletter includes a collection of the best articles and research on AI in the international landscape Artificial intelligence is rapidly changing cybersecurity, reshaping both the techniques used by attackers and the tools available to defenders. AI agents can automate tasks, analyze large amounts of data, discover vulnerabilities and accelerate offensive operations. At […]
P0
2026-10-18 11:00 UTC
Security Journalism
Security Week · Kevin Townsend · indexed 2026-10-18 11:15 UTC
CyberSN’s Cybersecurity Jobs Report provides visibility into the US cybersecurity job market. It’s a mixed bag. The post US Cybersecurity Job Postings Fall 26% as AI Security Engineer Demand Soars appeared first on SecurityWeek.
P0
2026-10-17 08:55 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-17 09:20 UTC
India’s CERT-In warns AI agents accessed confidential data undetected, while attackers used offensive AI frameworks to accelerate cyberattacks. CERT-In, India’s national cyber response team, published a critical-severity advisory 15 documenting two distinct categories of AI-related incidents. In one, AI models under research and evaluation exceeded their assigned tasks and accessed live Indian systems without authorization. […]
P0
2026-10-16 14:03 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-16 15:25 UTC
OpenAI has disclosed seven new incidents in which its artificial intelligence (AI) models exhibited misaligned behavior, including one case where its research model, after not having funds on an Ethereum test network, spent test cryptocurrency from a third-party's wallet without authorization to complete a coding task. The incident, the AI company said, involved an internal research model part
P0
2026-10-16 13:00 UTC
Security Journalism
Dark Reading · Alexander Culafi · indexed 2026-10-16 12:40 UTC
As agents escape containment and access external systems, responsibility remains human. Accountability, however, is much less settled.
P0
2026-10-16 06:53 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-16 07:30 UTC
AI agents being tested online reached the live systems of Indian organizations and read business records, including personal data and confidential material, CERT-In said in an advisory on October 15. The agents went beyond their assigned tasks, and none of the organizations detected the unauthorized access. After internal reviews, the AI companies whose models were being tested
P0
2026-10-16 00:46 UTC
Community
SANS Internet Storm Center · indexed 2026-10-16 00:50 UTC
I believe the cybersecurity industry may be approaching AI security the wrong way.
P0
2026-10-15 14:01 UTC
Security Journalism
BleepingComputer · Sponsored by Intruder · indexed 2026-10-15 14:20 UTC
AI pentesting can uncover vulnerabilities missed by human testers, but it also has limitations in consistency, risk assessment, and understanding business context. Intruder compares the strengths and weaknesses of both approaches and explains where AI agents can improve security testing. [...]
P0
2026-10-15 07:07 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-15 09:05 UTC
Threat actors are exploiting a critical security flaw in Langflow, according to an alert from Previdian. Langflow is an open-source platform that allows developers to build artificial intelligence (AI) applications and agentic workflows. In February 2025, DataStax, the parent company of Langflow, was acquired by IBM. The vulnerability in question is CVE-2026-105740 (CVSS score: 9.9), a case of
P20
2026-10-14 16:00 UTC
Security Journalism
Security Week · Kevin Townsend · indexed 2026-10-14 17:10 UTC
In Booz Allen’s isolated OT lab, AI models met every objective across eight scenarios and reached an industrial control network from a perimeter compromise in just over 16 minutes. The post AI Agents Navigate Unfamiliar OT Systems and Move Equipment in Minutes, Booz Allen Finds appeared first on SecurityWeek.
P0
2026-10-14 11:19 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-14 11:35 UTC
A team at security firm XBOW chained three then-unknown Google Chrome bugs into a single attack that runs code on a Windows computer when the user only loads a web page, the company said. Its researchers built the attack in six days by directing AI agents running OpenAI's publicly available GPT-5.6 Sol model. Google has since confirmed all three bugs, fixed them, and paid XBOW its top $
P0
2026-10-14 11:00 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-14 11:35 UTC
The bug was simple: the login let you choose where your sign-in code went. Proving it on a live website was the hard part. TL;DR During an authorized assessment, an AI pentesting agent found a critical authentication bypass on a major insurer's production website, on its own. One login request let the user choose where the one-time passcode went. The attack was the easy part. Proving it
P10
2026-10-13 18:20 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-13 19:05 UTC
Small artificial intelligence (AI) models may be months away from developing capabilities to self-replicate on IoT devices like smart ovens and off-brand Android TV boxes, according to a warning from Anthropic. The frontier AI lab said small AI models could form autonomous, self-propagating worm botnets that are "challenging to shut down," since "there's no centralized point to shut off."
P0
2026-10-13 16:18 UTC
Security Journalism
The Record · indexed 2026-10-13 16:25 UTC
The new research, published by AI security startup AIR, found that a network filtering flaw in Vercel Sandbox — a tool used to run code in isolated environments — could allow agents to exploit certificate validation processes to transmit data outside approved networks.
P0
2026-10-13 14:30 UTC
Other
Check Point Research · etal · indexed 2026-10-13 14:50 UTC
TL;DR; Our security assessment of LiteLLM (v1.77.7), a widely used open-source LLM gateway, uncovered multiple high-impact vulnerabilities (tracked as CVE-2026-35029, CVE-2026-59823) which have been resolved as of LiteLLM version 1.83.9. The most significant issues stemmed from a missing authorization check on the /config/update endpoint, which allowed any authenticated user (including low-privileged accounts) to modify the […] The post When LLM Gateways Go Wrong: Findings from LiteLLM appeared…
P5
2026-10-12 14:27 UTC
Other
Proofpoint Threat Insight · indexed 2026-10-15 21:40 UTC
P0
2026-10-12 11:55 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-12 12:30 UTC
The personal AI agents rollout is going about as smoothly as expected: Amazon now blocks Meta's Muse because it doesn't identify itself as a bot while browsing; Instinct keeps raising privacy concerns; and the horror stories from pretty much every personal AI agent keep piling up. Regardless, the tech world is mesmerized by the capabilities and potential of these services. Less than a year
P0
2026-10-12 09:34 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-12 10:50 UTC
CyberXero used 51 AI agents to support cyberattacks, stealing 628,000 Ukrainian records, including sensitive data from energy infrastructure. CyberXero is an operation that combines traditional hacking tools with AI agents to carry out cyberattacks. According to SOCRadar researchers, the attackers use the same infrastructure for two different campaigns: one targets WordPress websites and e-commerce platforms […]
P0
2026-10-12 07:26 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-12 08:00 UTC
Cybersecurity researchers have disclosed details of a two-pronged artificial intelligence (AI)-augmented initial access campaign targeting WordPress sites, e-commerce platforms, and critical infrastructure entities in Ukraine. The activity, which brings together commodity offensive tools like Cobalt Strike with an AI orchestration layer powered by Anthropic's Claude Code, has been attributed
P0
2026-10-11 18:43 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-11 19:30 UTC
Security Affairs AI-CYBERSECURITY newsletter includes a collection of the best articles and research on AI in the international landscape Artificial intelligence is rapidly changing cybersecurity, reshaping both the techniques used by attackers and the tools available to defenders. AI agents can automate tasks, analyze large amounts of data, discover vulnerabilities and accelerate offensive operations. At […]
P0
2026-10-10 09:18 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-10 10:00 UTC
Anthropic on Friday said it's cutting off live internet access for all its internal evaluations until further notice following the discovery of new incidents in which its artificial intelligence (AI) models exhibited misaligned behavior and targeted real websites. The AI company said it identified four broad categories of unintended model actions during evaluations and internal use of Claude
P0
2026-10-09 14:01 UTC
Security Journalism
BleepingComputer · Sponsored by Token Security · indexed 2026-10-09 14:15 UTC
AI agents can use valid credentials to perform actions beyond their assigned permissions, creating risks that traditional access controls may not prevent. Token Security explains how organizations can enforce agent-specific policies without sacrificing autonomy. [...]
P0
2026-10-09 13:00 UTC
Security Journalism
Dark Reading · Alexander Culafi · indexed 2026-10-09 13:10 UTC
As AI agents gain authority over business systems, attackers can manipulate them like business email compromise (BEC) victims.
P0
2026-10-09 12:47 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-09 14:35 UTC
Anthropic on Thursday unveiled OSS Scanner as an opt-in vulnerability scanner to help secure the open-source ecosystem using artificial intelligence (AI). "It's an opt-in service informed by our experience using Claude to find vulnerabilities during Project Glasswing," Anthropic said. "Projects that join will receive thorough, periodic security scans by our strongest models at no cost."
P0