LATEST

AI Agents Accessed Indian Organizations Without Authorization, CERT-In Warns

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. […]

OpenAI Research Model Spent 3rd-Party Test ETH Without Permission to Deploy Smart Contract

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

When AI Agents Commit Breaches, Humans May Not Be Held Liable

As agents escape containment and access external systems, responsibility remains human. Accountability, however, is much less settled.

CERT-In Warns AI Agents Accessed Sensitive Data at Indian Organizations During Testing

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

Small Agents, Smaller Blast Radius: Controlling What AI Can Do, (Fri, Oct 16th)

I believe the cybersecurity industry may be approaching AI security the wrong way.

Is AI pentesting as good as a human pentester?

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. [...]

Langflow's Critical Authenticated RCE Flaw Targeted in 1,423 Honeypot Exploit Attempts

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

AI Agents Navigate Unfamiliar OT Systems and Move Equipment in Minutes, Booz Allen Finds

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.

Researchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six Days

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 $

An AI Agent Found a Critical OTP Bypass in Production. The Attack Was the Easy Part.

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

Anthropic Warns Small AI Models Could Soon Form Self-Propagating IoT Botnets

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."

Sandbox vulnerability gives rogue AI agents a path to escape and leak data, research says

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.

When LLM Gateways Go Wrong: Findings from LiteLLM

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…

The Hidden AI Security Risks Threatening Businesses

Bring Your Own Agent: Your Employees' Assistants Are Already Logged In

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

CyberXero Used 51 AI Agents to Steal 628,000 Ukrainian Records

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 […]

CyberXero Uses Claude Code in Campaign That Stole Over 628,000 Ukrainian Records

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

SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 3

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 […]

Anthropic Cuts Live Internet Access for Internal AI Tests After Claude Exploits Injection Flaws

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

How to keep AI agents within their permissions

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. [...]

Social Engineering AI Agents: The New BEC for 2026

As AI agents gain authority over business systems, attackers can manipulate them like business email compromise (BEC) victims.

Anthropic Launches Free AI Vulnerability Scanner for Open-Source Projects

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."

The AI Velocity Paradox: Why Security Is Decades Behind AI Ambition

As enterprises race to deploy autonomous AI agents to accelerate business, a new report reveals they are tethered to security architectures built for a different era. The "Horizons of Identity Security" report from SailPoint highlights a critical “velocity paradox,” in which organizations invest in AI-speed business operations while continuing to rely on human-speed security controls, creating a

AI-Driven tool ARTEX used in attacks against South Korean Banks

CrowdStrike analyzes open directories left by an attacker who used the ARTEX AI pentest tool and LLMs to breach South Korean financial firms. CrowdStrike published a research on a campaign against South Korean financial organizations that ran from late September to early October 2026 and ended with stolen data. The attacker left their working notes […]

Reconstructing AI Agent Activity: Two New Scripts for Forensic Review, (Thu, Oct 8th)

We just did a major update to FOR577 and added a lot of new material on day 5 about investigating AI usage in incident response. In the new material we dicsuss 8 of the most popular AI coding assistants and agents including Claude Code, Codex, Gemini CLI, Cursor, Copilot, Warp, Windsurf, and Qwen Code. I've been using Claude Code and a little bit of Codex, but I also have recently been playing with OpenCode and am setting up Hermes. I decided t…

ARTEX AI Pentesting Tool Used in Data Theft Attacks on South Korean Financial Firms

Cybersecurity researchers have disclosed details of a targeted campaign aimed at South Korean financial organizations that used an artificial intelligence (AI) pen testing tool named ARTEX to carry out the attacks. The activity, per CrowdStrike Intelligence, was active from late September to early October 2026, and resulted in data exfiltration from various South Korea-based financial firms,

OAuth grants pile up faster than you can review them. Here's how to keep up.

OAuth grants create data highways between SaaS apps, AI agents, and other tools. And, they are multiplying faster than any security team can review them. As the recent Klue breach showed, attackers are taking notice and exploiting forgotten OAuth grants to gain access to corporate data. This article covers why OAuth risks are so hard [...]

Inside the Exchange Inspector: How Tenable uses OpenAI GPT cyber models to review open-source AI agents

Community-built AI agents, skills, and MCP servers are landing in SOC workflows fast. Here’s what the Exchange Inspector tests before a listing earns its vetted tag on the CyberAgents Exchange. Three tools have already passed.Key takeawaysEvery Inspector-vetted listing clears three gates: an automated check, a frontier model assessment, and human verification. Tenable uses Tenable One AI Exposure to screen for prompt injection and exposed secrets, and OpenAI GPT Cyber models to assess the code …

Rein Security Raises $25 Million to Guard AI Agents at Runtime

The cybersecurity startup will invest in product innovation, agentic research, and employee base expansion. The post Rein Security Raises $25 Million to Guard AI Agents at Runtime appeared first on SecurityWeek.

Anthropic Gives Vetted Defenders Fewer Claude Guardrails

Anthropic has merged Project Glasswing into a tiered access program for its advanced cyber LLMs, including Opus, Sonnet, and Mythos.