VOLTA is a mature stealer implant with an optional AI-integration layer. After stealing credentials, sessions, and cryptocurrency wallets, VOLTA sends a structured evidence bundle to an LLM to rank the victim’s assets by monetization value. If a model refuses to perform the target assessment, VOLTA fails over to a three-model chain, implying a direct engineering effort and expectation of hitting model guardrails. This stealer is self-deleting, and there is no attacker-owned infrastructure. The…
A malicious version of Anthropic's Claude Code VS Code extension was distributed through Cursor's extension marketplace for approximately 11 hours on October 29, exposing up to 5,000 developers to malware designed to install persistent SSH backdoors. [...]
Phishing remained the leading initial access technique, appearing in slightly over one-third of all Cisco Talos Incident Response (Talos IR) engagements — a decrease from over 50 percent last quarter. In addition to traditional phishing links and attachments, we observed numerous threat actors conducting voice phishing (vishing) in tandem with IT desk impersonation to socially engineer the victim into allowing remote access via a legitimate remote monitoring and management (RMM) tool.…
Key Points Check Point Research discovered a campaign we track as Yoba where attackers abuse the popularity of AI tools such as ChatGPT and Claude, creating fake GitHub projects that pretend to be desktop applications like GPT-5.6 Sol, GPT-6 Astra, and Claude Opus. The malware is placed next to legitimate, signed executables from OpenAI and Anthropic so it can be loaded indirectly, a technique commonly known as DLL sideloading, which is often used to bypass security protections. This campaign…
Police tip hotlines already have their fair share of crank callers. Apparently they now have to contend with crank AI agents as well. AI agents have already been caught hacking software companies, breaching an Australian government portal, and trying to hack a Canadian government website. Now Anthropic’s Claude has added a made-up murder tip to the list. Claude’s Haiku 4.5 model filed a false tip in an unsolved Philadelphia homicide via the police department’s online public tip form, Anthropic…
Anthropic announced that its internal AI models undergoing "high-risk and cybersecurity evaluations" no longer have internet access following incidents involving U.S. government websites at the federal, state, and local levels. [...]
Phishing follows whatever people want at the moment, and right now that includes AI subscriptions they don’t have to pay for. We recently uncovered a new variation on this theme: A fake Claude Max giveaway that uses a convincing Google sign-in window to steal login information.Claude’s paid plans start at $20 a month and cost considerably more for higher usage limits, while free accounts have stricter limits. That makes the promise of a free upgrade an attractive lure.Microsoft reported in June…
This week on the Lock and Code podcast… If you want AI to tell you a story, it will. If you want that story to sound like one of your favorite authors, it can. And if you’re one of the authors that AI can imitate, you might be a little upset at what feels like theft. In 2024, the authors Andrea Bartz, Charles Graeber, and Kirk Wallace Johnson sued Anthropic, the creator of Claude, alleging that the company had wrongfully digested millions of copyrighted works—including some of their very own—to…
Google says one of its Gemini models accessed systems belonging to three real companies during a cybersecurity evaluation in May. The model reportedly guessed credentials in one case, while finding exposed credentials in public repositories in two others. Google says Gemini stopped once it recognized that it had reached real infrastructure and that the affected organizations were notified. Gemini was participating in an evaluation run by Irregular, a third-party AI cybersecurity testing firm.…
The defining development of the period came not from attackers but from the AI labs themselves, whose models broke out of controlled evaluations and reached real systems. In the wild, the criminal and state use of AI continued to mature along the lines tracked in earlier editions: models now act as attack operators, an underground market supplies the access, and AI systems have themselves become a target. The substantial distance between what the strongest models demonstrated under evaluation…
The tech journalists at 404 Media learned that OpenAI is hiring hundreds of contractors to read and review a massive stream of real users’ ChatGPT prompts and responses. “Project Lily” is reportedly a program that asks contractors to score or critique ChatGPT’s answers to improve the chatbot’s quality and behavior. The fact that prompts may sometimes be reviewed by humans should not come as a complete surprise. AI companies also monitor conversations for safety reasons. Anthropic, for example,…
China's spy chief identified Anthropic’s Claude Mythos and OpenAI’s GPT-5.5-Cyber as signs of what he called a “disruptive upgrade” in cyber capabilities, increasing the speed and potential weaponization of vulnerability discovery and malware development.
For the latest discoveries in cyber research for the week of 14th Setpember, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES IDScan.net, a US identity verification provider, has disclosed a data breach after detecting unauthorized access on September 1. Exposed data included names and government identification numbers, while a criminal marketplace advertised a collection containing millions of identity documents, including driver’s licenses, associated with the…
Anthropic says multiple threat groups, including the financially motivated and state-sponsored espionage groups linked to Russia and China, tried to abuse its Claude AI model for malicious purposes. [...]
Anthropic detected and disrupted a Russia-linked cyber-espionage group that used its AI tool Claude in a hacking campaign targeting more than 20 government, intelligence, diplomatic and defense organizations.
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…
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…
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…
Selecting a model for your security operations center (SOC) and digital forensics and incident response (DFIR) tasks is important, but selecting the best one is more involved than you might think. SOC tasks rely on a combination of model efficacy, analysis time, cost, and consistency of results. Cisco Talos tested 66 model and reasoning combinations across offerings from both Anthropic and OpenAI on a log analysis task to see if we could identify a clear winner. Instead, we found a repeatable…
GreyNoise is observing automated scanners posing as the web crawlers of OpenAI, Anthropic, DeepSeek, and Fortune 500 companies, using forged user agents while requesting the files where misconfigured web servers frequently leak secrets and credentials.
As frontier models advance in cyber capability, their guardrails also become more restrictive. Defenders relying on these models to power core SOC processes cannot afford to pay the “safety penalty” of being blocked by these safeguards. Organizations should monitor model refusal rates and use the data to create a strategy to ensure operational sovereignty.The allure of the cloud and the hidden "safety penalty" Cybersecurity has made a big bet on cloud-hosted AI. Building and running frontier…
An autonomous AI breach at Hugging Face and Anthropic's Fable suspension show the same thing: trusting a vendor isn't the same as being in control Category: News
Executive Summary Four incidents involving OpenAI, Anthropic, Meta and the UK AI Security Institute (AISI) describe AI agents reaching systems belonging to other organizations without their consent. While the causes differ, the consistent factor is the models’ persistence rather than their sophistication, whether as endurance across days of failed attempts or as pivots to entirely new vectors. Security teams have traditionally studied the artifacts attackers leave behind, but an agent that…
For the latest discoveries in cyber research for the week of 10th August, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES North Carolina Ports, the US authority operating the ports of Wilmington, Morehead City and others, has suffered a cyberattack that forced some operations onto manual processes. The authority claims it has contained the intrusion, but degraded systems caused delays while affected services were restored. Ryde, an electric scooter operator in…
We spent 500+ hours and 40 billion tokens testing Anthropic’s Claude Mythos Preview for Project Glasswing. The takeaway: frontier AI won't run your code security program, but used well, it can make one even stronger.Key takeawaysFrontier AI dramatically scales security testing. In one month, Tenable dedicated 11 security experts and more than 40 billion tokens testing Claude Mythos Preview across source code analysis, exploit creation, binary reverse engineering, threat modeling, and dynamic…
Tenable spent 30 days running frontier AI models against our own code. It didn’t just find bugs — it proved they’re real, with reproducible exploits. That fundamentally changes code security from ranking potential code defects to a much higher signal focused on the findings that matter. Read on to learn how it reshaped our security team's work, what it cost, and why your program is next.Key takeaways:Now code security starts with proof, not suspicions. Frontier AI instantly builds working…
Anthropic disclosed an agent that pushed real malware to PyPI. We think we found the package, and every mistake in it points back to the AI. Category: Vulnerabilities & Threats
Executive Summary SentinelLABS developed a multi-stage reverse-engineering benchmark for the latest generation of frontier models by recreating our recent investigation of fast16, a unique 2005 sabotage implant. Most AI benchmarks test bounded tasks. This benchmark tests whether a model can keep a malware investigation trustworthy as new evidence repeatedly invalidates its earlier conclusions. OpenAI’s GPT-5.6 Sol was the only publicly available model to complete the full eight-stage…
Executive Summary Compaction is a context-management pattern used across agent systems to compress prior context into a denser working state for long-running tasks. SentinelLABS evaluated OpenAI’s native Responses API implementation against our automated malware analysis evaluation harness to measure real-world impact on task quality and cost. Compaction reduced input tokens by ~86% with no measurable change to the aggregate evaluation score. Our analysis found that compaction can significantly…
You never needed Mythos to find your IDORs and business logic flaws. A look at what Anthropic shipped with Fable 5, and why infosec stays a people problem at heart. Category: News
As AI coding assistants become standard tools in engineering workflows, security teams face a new challenge: how do you maintain visibility into what an AI agent is doing (and why) across your organization? When those agents can execute shell commands, read files, call APIs, and interact with internal systems via MCP connectors, you need real-time observability to support threat detection, incident response, and compliance. This post walks through how Elastic's InfoSec team built a monitoring…
Threat actors leveraged Anthropic’s Claude Code npm release packaging error to distribute Vidar, GhostSocks, and PureLog Stealer. This blog details immediate steps organizations can take and best practices to prevent further risk.
A packaging error in Anthropic’s Claude Code npm release briefly exposed internal source code. This entry examines how threat actors rapidly weaponized the resulting attention, pivoting an existing AI-themed campaign to spread Vidar and GhostSocks.