Tag: attack
-
Claude Code and Gemini CLI Flaws Let a GitHub Issue Reach CI Workflow Secrets
A GitHub issue opened by an account with no repository privileges was enough to execute code on the CI runners behind Anthropic’s and Google’s own coding-agent repositories. On OpenAI’s, it was enough to hijack the next agent run.Novee Security ran the attack against each vendor’s agent in the configuration that the vendor ships by default,…
-
What is Penetration Testing?
Penetration testing, commonly known as “pen testing,” is an authorised attack where trusted cyber security experts evaluate physical and digital systems, networks, or applications. It … Read more First seen on securityboulevard.com Jump to article: https://securityboulevard.com/2026/08/what-is-penetration-testing-2/
-
TeamPCP Linked To Redis Attacks Dating Back To 2020 And Later Supply Chain Campaign
Tags: attack, cybercrime, group, infrastructure, Internet, malware, software, supply-chain, threat, trainingA new analysis has uncovered that the threat actor tracked as TeamPCP has been active on the cybercrime scene as far back as 2020, indicating the group has been compromising internet-facing infrastructure for years before training their sights on the software supply chain.”The connection is supported by overlapping domains, malware deployment paths, staging techniques, backend…
-
Hackers Can Abuse Microsoft WSUS Servers to Deploy Malicious Updates via NTLM Relay
Security researchers have shown how attackers could exploit Microsoft Windows Server Update Services (WSUS) infrastructure to distribute malicious software updates across enterprise networks. This technique relies on NTLM authentication coercion and relay attacks targeting WSUS deployments that utilize a separate Microsoft SQL Server database. WSUS is commonly used by organizations to centrally manage, approve, and…
-
Critical Flaws in Claude Code, Gemini CLI, and OpenAI Codex Enable RCE and Supply Chain Attacks
Tags: ai, attack, automation, breach, cyber, flaw, google, openai, rce, remote-code-execution, supply-chain, theft, tool, vulnerabilitySecurity researchers have disclosed a vulnerability affecting AI coding-agent workflows from Anthropic, Google, and OpenAI. Their research highlights how an attacker-controlled issue or zero-privilege input can breach trust boundaries in an agent “harness”, which includes the permissions, tools, sandbox, filesystem, and automation surrounding the model, and result in code execution, secret theft, or workflow compromise.…
-
Apiiro’s Idan Plotnik on AI writing code that sharpens attacks
First seen on scworld.com Jump to article: www.scworld.com/resource/apiiros-idan-plotnik-on-ai-writing-code-that-sharpens-attacks
-
Top 10 Best External Attack Surface Management (EASM) Platforms 2026
In the sprawling digital ecosystem of 2026, organizations grapple with an increasingly complex and often poorly understood external attack surface. This attack surface encompasses all internet-facing assets that are discoverable and potentially exploitable by malicious actors. These assets extend far beyond traditional network perimeters to include cloud resources, web applications, APIs, orphaned infrastructure, exposed databases,…
-
ClickFix attack pushes macOS infostealer for crypto theft attacks
A Go-based malware delivered in ClickFix attacks targeting macOS users is stealing cryptocurrency assets, browser-stored passwords, Apple Keychain data, and cached credentials. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/security/clickfix-attack-pushes-macos-infostealer-for-crypto-theft-attacks/
-
AI Accelerates Financial Services Fraud
Coinbase’s Lunglhofer on Deepfakes, Supply-Chain Risk and Human Expertise. AI is helping criminals clone voices, exploit software flaws and guide fraud schemes in real time. Coinbase Chief Security Officer Jeff Lunglhofer explains why faster attacks demand AI-enabled defense backed by cybersecurity experts. First seen on govinfosecurity.com Jump to article: www.govinfosecurity.com/ai-accelerates-financial-services-fraud-a-32450
-
How Agentic AI Scales Cybercrime
Google’s Hultquist on Autonomous Attacks and Behavioral Defense. Cybercriminals are using agentic AI to automate intrusions, rewrite malware and scale operations with stolen access to artificial intelligence services. Google’s John Hultquist explains why signature-based defenses are losing ground and how behavioral detection can help security teams respond. First seen on govinfosecurity.com Jump to article: www.govinfosecurity.com/how-agentic-ai-scales-cybercrime-a-32449
-
Researcher Claims Control of ChatGPT Secure Sandbox
A researcher demonstrated a proof-of-concept attack chain that provided C2-style influence over ChatGPT’s isolated sandbox during a session at Black Hat USA 2026. First seen on darkreading.com Jump to article: www.darkreading.com/cloud-security/researcher-claims-control-chatgpt-secure-sandbox
-
Why Open-Weight AI Models Are Key to US Strategy
Rain Capital’s Chenxi Wang on Why Closed AI Models Risk US Competitiveness. Machine-scale AI attacks demand machine-scale defenses, says Rain Capital’s Chenxi Wang. She says America’s edge depends on backing open-weight models and using the world’s top AI researchers, not retreating behind closed systems that cede ground to competitors. First seen on govinfosecurity.com Jump to…
-
New TONTOU CPU attack bypasses Spectre v2 fixes, leaks Linux password hashes
Researchers found a way to bypass recent mitigations for Spectre v2 speculative execution side-channel attacks and developed an exploit to leak secrets from Linux machines. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/security/new-tontou-cpu-attack-bypasses-spectre-v2-fixes-leaks-linux-password-hashes/
-
New Interrupt Injection Attack Can Bypass Spectre v2 Defenses on Intel and AMD CPUs
An unprivileged Linux program can time a hardware interrupt to land in the gap between a processor sanitizing its branch predictor and the kernel using it, re-poisoning the predictor after the defense has run.MIT CSAIL researchers Daniël Trujillo and Mengjia Yan named the technique INTERRUPT INJECTION. On an AMD Zen 2 machine running Linux 6.14…
-
Zenity Labs Finds Zero-Click Attack Chains Across Agentic Browsers
Zenity Labs released research at Black Hat USA 2026 showing zero-click PleaseFix exploit chains across Claude in Chrome, Gemini in Chrome, Perplexity Comet, ChatGPT Atlas and Copilot Edge. The attacks demonstrated paths to silent data theft, credential theft, account takeover and remote control of a victim’s machine. PleaseFix abuses the way agentic browsers combine information..…
-
Over 4,400 Rockwell PLCs Exposed Online, 22 Found in Water Attack Cities
Forescout found 22 internet-facing Rockwell Automation programmable logic controllers (PLCs) in cities hit by recent cyberattacks on US water utilities. Nineteen used the same mobile carrier network.Its August 3 scan counted 4,407 exposed Rockwell controllers worldwide, including 2,844 in the United States, but Forescout could not confirm any were compromised. That figure counts exposed First…
-
Defending Water OT with AZT PROTECT – ARIA Cybersecurity
<div cla The threat landscape for municipal water systems has never been more perilous, and the regulatory spotlight has never been brighter. A flurry of attacks has taken over the news: in some cases, ransomware-based attacks cripple water production and in other cases controls on individual unprotected PLCs are being suddenly accessed by bad actors…
-
How AZT Breaks the Hugging Face Attack Chain – ARIA Cybersecurity
<div cla A clear, practical look at how endpoint and in-memory whitelisting stops a machine-speed intrusion. Machine-speed attacks need deterministic trust enforcement. AZT SECURITY ANALYSIS – AUGUST 2026 First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/08/how-azt-breaks-the-hugging-face-attack-chain-aria-cybersecurity/
-
Alarm sounded around supply chain risks
With AI agents demonstrating their ability to bypass security, the need to protect against attacks originating from third-party suppliers has increased First seen on computerweekly.com Jump to article: www.computerweekly.com/microscope/news/366648132/Alarm-sounded-around-supply-chain-risks
-
Meta Confirms AI Model Launched Autonomous Attack on Another Organization
Meta has become the latest technology company to disclose that an AI agent accessed another organization’s online systems during a controlled cybersecurity evaluation. This development has intensified scrutiny regarding the safeguards surrounding autonomous models and the testing environments for agentic AI. The incident reportedly occurred when a Meta AI model, evaluated by the independent security…
-
The water sector just got it’s wake-up call. Again.
Tags: attackThe attack on water systems across seven states was preventable. Utilities had the playbook. They didn’t use it. First seen on cyberscoop.com Jump to article: cyberscoop.com/water-utility-cyberattacks-prevention-nozomi-networks-ceo-op-ed/
-
AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model
Security flaws in agent infrastructure from Amazon Web Services (AWS), Google, and Vercel let untrusted or forged instructions reach an agent’s tools with no check that a model turn had authorized them.In several of the attack paths, the model never ran at all, so system prompts, content filters, and model-level guardrails never got a chance…
-
South Korea’s government overtakes telcos as top cyber attack target
Kaspersky researcher Sojun Ryu says ransomware crews have joined nation-state groups in going after South Korean organisations, as traces of LLM output start turning up inside malware First seen on computerweekly.com Jump to article: www.computerweekly.com/news/366647735/South-Koreas-government-overtakes-telcos-as-top-cyber-attack-target
-
Why Post-Quantum Security Is Climbing the Enterprise Agenda
Tags: ai, attack, computer, computing, conference, container, crypto, cryptography, cybersecurity, data, google, government, hacker, Hardware, ibm, infrastructure, intelligence, risk, technology, threat, toolWhy Post-Quantum Security Is Climbing the Enterprise Agenda andrew.gertz@t“¦ Thu, 08/06/2026 – 04:56 Learn why post-quantum security is becoming an enterprise priority, how AI and quantum computing are reshaping cryptography, and how Thales Luna 8 helps organizations prepare. Data Security Key Management Encryption Key Management Bree Fowler – Journalist More About This Author > At…
-
Palo Alto Networks Introduces PAN-OS 12.2 Ceres With AI Security Features
Palo Alto Networks has introduced PAN-OS 12.2 Ceres, a firewall operating system update that adds more than 55 innovations aimed at attacks accelerated by frontier AI. The release centers on Advanced Virtual Patching, Advanced IP Defense and six AI-powered Network Security Agents. Advanced Virtual Patching uses AI to identify unknown vulnerabilities and deliver network protections..…
-
VanishID Previews AI Exploitability Management at Black Hat USA 2026
VanishID has unveiled AI Exploitability Management, a capability designed to measure what frontier AI could build from publicly exposed information about an organization’s people. The company is demonstrating the capability publicly for the first time at Black Hat USA 2026. VanishID said the system evaluates more than 40 AI-powered attack scenarios, including executive impersonation, real-time..…
-
Suppliers, logins, and AI tools are all becoming attack paths
Cybercriminals and state-backed hacking groups are abusing trusted identities, cloud services, AI tools, and software supply chains to gain access while avoiding detection, … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/08/06/crowdstrike-cyber-threat-trends-report/