This vulnerability allows remote attackers to execute arbitrary code on affected installations of OpenAI Codex. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-19592.
EPSS 0.00 CVSS 7.8 CVE-2026-19592 OpenAI US
This vulnerability allows remote attackers to execute arbitrary code on affected installations of OpenAI Codex. User interaction is required to exploit this vulnerability in that the target must open a malicious folder. The ZDI has assigned a CVSS rating of 7.8. The following CVEs are assigned: CVE-2026-19593.
EPSS 0.00 CVSS 7.8 CVE-2026-19593 OpenAI US
US
U.S. cybersecurity and intelligence agencies say that six Chinese AI companies conducted industrial-scale distillation attacks on American frontier AI models since at least late 2024. [...]
US
Serial Number: AV26-900Date: September 9, 2026 As of September 8, 2026, NVIDIA is affected by vulnerabilities in the following product: Triton Inference Server Versions 0.0 to 26.03 Versions 0.0 to 26.06 The Cyber Centre encourages users and administrators to review the provided web links and apply any necessary updates as they become available. Security Bulletin: Triton Inference Server - September 2026 NVIDIA Product Security
NVIDIA CA
The question of whether a Frontier AI model could find vulnerabilities that no human researcher had found was settled in April. Claude Mythos Preview identified thousands of previously unknown flaws across every major operating system and browser, including a 27-year-old denial-of-service condition in OpenBSD, and within a month Anthropic and its Project Glasswing partners had logged more than 10,000 high and critical severity findings, among them a certificate forgery flaw in wolfSSL, a…
Open-source registries for AI agents are only effective when they include a rigorous, transparent security review process for community submissions. That’s why for its new CyberAgents Exchange registry, Tenable paired its exposure management expertise with OpenAI GPT Cyber models to create the CyberAgents Exchange AI Inspector.Key takeawaysThe Exchange Inspector combines Tenable’s exposure detection with OpenAI’s GPT Cyber models and with human oversight to rigorously vet submissions made to…
AI scams are now hyper-realistic. But there’s one simple way to see through them.
SK
An Ohio man was sentenced to 15 years in prison for multiple cybercrimes, including sextortion and cyberstalking of numerous victims using AI-generated sexually explicit content. [...]
US
This vulnerability allows remote attackers to execute arbitrary code on affected installations of Flowise. Authentication is not required to exploit this vulnerability. The ZDI has assigned a CVSS rating of 9.8. The following CVEs are assigned: CVE-2026-70477.
EPSS 0.01 CVSS 9.8 CVE-2026-70477 Flowise US
US
Classification: Critical, Solution: Official Fix, Exploit Maturity: Unproven, CVSSv3.1: 9.9, CVEs: CVE-2026-12744, CVE-2026-12745, CVE-2026-12651, CVE-2026-12650, CVE-2026-12648, CVE-2026-12645, CVE-2026-12646, CVE-2026-12647, Summary: Ivanti has released updates for Ivanti Neurons for ITSM (N-ITSM) which addresses High and Critical severity vulnerabilities. We are not aware of any customers being exploited by these vulnerabilities at the time of disclosure. Additionally, it’s important for…
EPSS 0.02 CVSS 9.9 CVE-2026-12645 CVE-2026-12646 CVE-2026-12647 CVE-2026-12648 CVE-2026-12650 CVE-2026-12651 CVE-2026-12744 CVE-2026-12745 Ivanti FI
11 organizations compromised in 26 seconds. GreyNoise breaks down the AI-enabled campaign against PaperCut that hit 440 instances across 48 countries.
PaperCut US
Proofpoint OpenAI US
The shift from AI-assisted tooling to agentic, AI-native security operations is no longer theoretical. It is entering production at scale, and 2026 represents the practical inflection point for enterprise SOCs. Agent frameworks are stabilizing, defenses against agent-specific attacks are maturing, and executive stakeholders increasingly demand AI-driven outcomes that are transparent, explainable, and auditable.[1]Nearly two-thirds of organizations are already experimenting with AI agents, yet…
Elastic US
Jason Haddix on why manual pentesting can't keep up, what disappears first, and why human methodology is what makes AI pentesting work Category: Guides & Best Practices
BE
Jason Haddix on why manual pentesting can't keep up, what disappears first, and why human methodology is what makes AI pentesting work Category: Guides & Best Practices
BE
Tenable is bringing Anthropic’s Claude Mythos 5 into our enterprise security offerings. Adding frontier adversarial reasoning to the Tenable One Exposure Management Platform will help customers better anticipate how attackers could breach their environments and stay ahead of AI-fueled risk. Tenable One Adversary View, the first innovation planned from this work, will debut in the coming weeks.Key takeawaysClaude Mythos 5 is coming to Tenable One. In addition to using Claude Mythos 5 for…
OpenAI confirmed that GPT-6 Astra is the first model it has broadly deployed to reach the "Critical level" for cybersecurity capabilities. [...]
OpenAI US
Insufficiently protected credentials in GitHub Copilot and Visual Studio Code allows an unauthorized attacker to disclose information over a network.
EPSS 0.01 CVE-2026-81381 GitHub US
Improper neutralization of special elements used in a command ('command injection') in GitHub Copilot and Visual Studio Code allows an unauthorized attacker to disclose information over a network.
EPSS 0.01 CVE-2026-81380 GitHub US
Research by: Alexey Bukhteyev Key Takeaways Check Point Research discovered a covert cross-account command channel through which an attacker could use a victim’s ChatGPT session to execute hidden tasks with the tools, data, and connected apps available to that session. The victim could receive a normal answer to their visible request while the attacker’s task was processed separately and its result returned across accounts. In our proof of concept, ChatGPT retrieved email data from the victim’s…
OpenAI IL
Executive Summary Since the release of our May 2026 report detailing adversarial misuse of artificial intelligence (AI), Google Threat Intelligence Group (GTIG) has observed forward leaning adversaries transition from basic prompting to agentic AI workflows and AI-enabled automation. In these operations, human-in-the-loop latency is dramatically reduced, compressing the traditional window for defenders to respond. In Q2 2026, GTIG observed threat actors compromise a cloud resource, then plan,…
PyPI npm Docker GitHub zdravotnictví veřejná správa média US
Threat actors are increasingly switching from AI-powered coding assistants to multi-agent frameworks that automate every stage of an attack. [...]
US
Executive summary China-based artificial intelligence (AI) companies are conducting systematic extraction of proprietary functionalities and capabilities of U.S. AI companies’ models through industrial-scale knowledge distillation campaigns that form the core—not merely a supplement—of their AI development strategy. While “distillation” is recognized as a legitimate and useful technique in AI research, China-based AI companies are engaging in aggressive, malicious, and targeted distillation…
US
For the latest discoveries in cyber research for the week of 7th Setpember, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES Thomson Reuters, a global information and technology company, has disclosed a breach of its C-Track court case-management platform affecting courts across 11 US states and Canada. An unauthorized party obtained C-Track files containing court records, including names and other personal information. Hit, a major Slovenian gambling and tourism…
KEV ✓ EPSS 0.09 CVSS 10.0 CVE-2026-82329 CVE-2026-83548 CVE-2026-83549 Thomson Reuters Dropbox SonicWall JFrog IL
The new Huntress AI SIEM search feature lets you find answers in plain English, with no query language fluency required. Ask questions, get results, and skip the syntax.
Huntress US
In a recent post, we looked at reports of League of Legends players receiving suspicious friend requests shortly after matches. The accounts quickly steered the conversation toward Discord, where they promoted paid adult-content pages. At the time, one unanswered question was how much of those conversations was automated. Were people working from scripts behind the accounts? Were they conventional, rules-based chatbots following a limited decision tree? Or were they using generative AI to…
OpenAI admits it did not disclose an incident where autonomous AI agents hijacked a German wiki, created 18,000 posts, shared answers, and bypassed restrictions, saying it treated the activity as model "misalignment" rather than a security breach. [...]
OpenAI US
Enterprises face an unmanaged crisis of AI agent and MCP server sprawl, characterized by rapid, decentralized proliferation of autonomous agents, protocol connections operating with excessive privilege, opaque execution paths, and identity blind spots. Absent agent-aware governance, modern enterprises struggle to prevent, detect, or contain multi-hop autonomous exploits, leaving environments vulnerable to lateral movement, shadow collaboration, and unauthorized data exfiltration. More…
In this article Edge AI changes the trust model for AI systemsConstrain model actions through deterministic mediationEstablish trust before releasing sensitive assetsVerify runtime before releasing sensitive assetsVerify artifacts that shape model behaviorNext steps Edge AI moves model execution, model IP, customer data, and system authority into infrastructure the customer owns and operates. That changes who must verify the stack before sensitive assets are released. Edge AI includes AI…
US
Want to know the latest from Google Cloud? Find it here in one handy location. Check back regularly for our newest updates, announcements, resources, events, learning opportunities, and more. Tip: Not sure where to find what you’re looking for on the Google Cloud blog? Start here: Google Cloud blog 101: Full list of topics, links, and resources. aside_block <ListValue: []> Aug 31 - Sept 4 Automate VM guest software lifecycle with VM Extension Manager, now GAGoogle Cloud VM Extension Manager is…
Google US
In this article What is ASCII smuggling?Writing a practical ASCII-smuggling signatureWhat we observed: ASCII smuggling repurposed for phishingWhat is known and what is newIs there a detection gap?Mitigation and protection guidanceReferencesLearn More Microsoft researchers observed a high-volume phishing campaign using invisible Unicode tag characters, a technique popularized in AI prompt injection research as ASCII Smuggling. Instead of using these characters to hide instructions from people…
FortiCNAPP analyzes an AWS LLMjacking incident involving a leaked administrator key and unauthorized access to Amazon Bedrock.
Amazon US
Shadow AI is spreading faster than governance in financial services. See the risks, why blocking AI backfires, and how to build policies that work.
finance US
US
Explore how attackers targeting Latin American entities use AI for data exfiltration and how basic OpSec errors allow defenders to disrupt operations. The post Attackers Expose Ongoing AI Tool Use Targeting Organizations in Latin America appeared first on Unit 42.
US
Classification: Critical, Solution: Unavailable, Exploit Maturity: Not Defined, CVSSv3.1: None, CVEs: CVE-2026-80047, Summary: A vulnerability in the Hugging Face Transformers library (versions 4.49.0 through 5.8.1) allows remote, attacker‑controlled Python files to be written to the local disk without user authorization. The library performs a remote module fetch and local cache write before evaluating the trust_remote_code consent prompt, violating the security contract enforced across other…
EPSS 0.00 CVE-2026-80047 Hugging Face FI
Don’t panic if you spot an illegally created image or video of you online – there are ways to request its removal
SK
Using autonomous AI agents, an attacker breached an enterprise network in a matter of hours. Understand how to address and defend against agentic attacks. The post An AI-Assisted Cyber Attack: Inside a Unit 42 Investigation appeared first on Unit 42.
US
You might tell an AI chatbot secrets that you wouldn’t divulge to your closest friends. If you do, though, beware: They could end up as evidence in court. An article in the Washington Post this week highlighted several cases in which people had discussed sensitive information with AI systems like Claude and ChatGPT, only to have their conversations obtained by prosecutors or opposing lawyers. Lawyers can get access to your chatbot conversations from AI services like ChatGPT because they aren’t…
OpenAI US
CrowdStrike US
CrowdStrike US
Threat actors are exploiting an unauthenticated remote code execution vulnerability (CVE-2026-0768) in Langflow, an open-source framework for building AI applications, to steal credentials, tokens, and keys. [...]
EPSS 0.08 CVE-2026-0768 Langflow US
Fileless execution on Linux has moved from niche tradecraft into real-world intrusion chains. By executing payloads from memory or anonymous file descriptors, attackers can reduce on-disk artifacts and weaken controls that rely heavily on file inspection.In our own analysis of VoidLink, we observed how fileless execution can be paired with a rootkit. The loader scans for processes running from memfd and passes their PIDs to the rootkit, allowing an already running fileless implant to be hidden…
Elastic US
Otvorene su prijave na 7. izdanje Hacknite – CTF natjecanja za srednje škole! Ovogodišnje natjecanje donosi nova pravila vezana uz prijavu i korištenje tehnologija umjetne inteligencije. Prilikom prijave timova u obrazac je potrebno upisati @skole.hr adrese prijavitelja i natjecatelja! Tijekom natjecanja je ograničeno korištenje AI alata, a detaljnu uputu što se smije, a što ne pronaći ćete u Pravilima na dnu stranice. Natjecanje u obliku CTF-a (Capture the Flag) namijenjeno je srednjoškolskim…
školství HR
Anthropic has warned some Claude users that criminals are using information stealers to take over their accounts. Rather than guessing passwords or intercepting two-factor authentication (2FA) codes, the attackers steal the browser sessions that prove a user is already logged in. According to a warning email shared publicly by an affected user, the attackers used common infostealer malware to copy Claude login sessions from victims’ computers. They then used those sessions to access the…
Anthropic US
CrowdStrike US
Introduction Beginning in 2024 Mandiant investigated a string of compromises affecting Brazilian financial services, retail, and eCommerce organizations. Google Threat Intelligence Group (GTIG) tracks this activity as BREEZE COMET (formerly UNC5669), a financially motivated threat actor specializing in manipulating payment systems and banking software in Brazil to conduct fraudulent transfers. This activity overlaps with operations publicly reported as Plump Spider and SHADOW-AETHER-064. In…
One of my internet-exposed inference honeypots was discovered, relabeled with sought-after model names, and incorporated into infrastructure apparently used to provide "free" LLM backends. It then received a real coding-agent session — history, filesystem output, working paths, and the agent's local tool manifest. The honeypot did not request or cause any tool execution; what the request exposed is what a malicious operator in that position could do. Chasing the "free API key" is not new. What…
opencode US
For the latest discoveries in cyber research for the week of 31st August, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES Manchester Airports Group, the UK operator of Manchester, London Stansted, and East Midlands airports, has disclosed a cyberattack that exposed data belonging to about 8.7 million customers. The compromised information includes contact details, vehicle registration numbers, and information collected through car park, lounge, fast-track, and Wi-Fi…
KEV ✓ EPSS 0.04 CVSS 10.0 CVE-2026-18885 CVE-2026-18886 CVE-2026-74820 CVE-2026-75604 CVE-2026-81578 CVE-2026-82078 PaperCut Ubiquiti Vercel ServiceNow IL
Rilevate 8 nuove vulnerabilità di sicurezza, di cui 2 con gravità “critica” e 4 con gravità “alta”, che interessano il software Langflow, nota piattaforma open-source che permette di costruire, testare e distribuire applicazioni e agenti basati su intelligenza artificiale.
EPSS 0.02 CVE-2026-18729 CVE-2026-18891 CVE-2026-18899 CVE-2026-18904 CVE-2026-19286 CVE-2026-19295 LangFlow IT
US
Today we’re announcing an expanded integration between GreyNoise and the CrowdStrike Falcon® platform, with new content for CrowdStrike Falcon® Next-Gen SIEM and CrowdStrike Charlotte Agentic SOAR. The expanded integration includes a purpose-built Falcon Next-Gen SIEM dashboard, correlation rules that detect allowed inbound traffic from malicious infrastructure, and SOAR playbooks that bring GreyNoise threat context into automated response workflows. Install the GreyNoise Foundry App to get…
CrowdStrike US
New research reveals that AI safety refusal lives in a thin neural layer, highlighting the critical need for external, multi-layered security. The post Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety appeared first on Unit 42.
US
AI is accelerating vulnerability discovery, putting pressure on systems built to enrich, prioritize, and remediate flaws at a slower pace. Action1 explains why defenders increasingly need to correlate multiple intelligence sources and turn vulnerability data into faster remediation. [...]
US
The hacking incident involving OpenAI evaluation agents and Hugging Face offers an unusually concrete look at what advanced AI-assisted intrusion can mean in practice: not a single clever exploit, but thousands of automated decisions, rapid experimentation, lateral movement, credential theft, persistence, and attempts to evade detection. The OpenAI–Hugging Face incident began during internal cybersecurity evaluations using ExploitGym, a benchmark designed to test whether AI agents can identify…
Welcome to this week’s edition of the Threat Source newsletter. Hello, everyone. Long time reader, first time writer here at the Threat Source newsletter! I wanted to start out by introducing myself. My colleague and friend Mick Baccio set the bar pretty high last week, so I was planning to tell you all about myself, including: How I did my first real IR under the influence of The Cuckoo’s Egg while an undergraduate (and failed) My pre-bug bounty flirtation with vulnerability research,…
Cisco US
As organizations incorporate AI agents into more processes across business and operations, security teams can benefit from greater visibility and new purpose-built tools that help manage, secure, and govern AI. This month’s updates provide new capabilities to help organizations gain insights into agent activity, expand security coverage across supported environments, and enhance security management across their environments. Here’s what’s new: Extend expert-led protection with new capabilities…
Microsoft US
Discover how Tenable’s shift to an AI-driven exposure management program helped Tenable’s CSO, Robert Huber, overcome tool sprawl, unify data silos, mitigate the risk of rapid AI adoption, and shift from presenting granular, technical metrics to communicating business risk that the C-suite and the board can understand.Key takeawaysSecurity tool sprawl and data silos make it difficult for CISOs to holistically and accurately assess their organizations’ cyber risk.An exposure management program…
Tenable US