







AI-orchestrated penetration testing platforms like ARTEX have become increasingly powerful tools enabling effective attacks on exposed infrastructure.
Criminals Have a New Favorite ‘Point-and-Shoot’ AI Hacking Tool
Artex and similar penetration testing tools allow newbie hackers to scan targeted systems for vulnerabilities and successfully wage attacks using prompts fed to chatbots.

Top AI Security Incidents of 2025 Revealed | Adversa AI
Discover how AI systems are being hacked in the wild — from prompt injection to agent abuse — with real breaches, lessons, and defenses in Adversa AI’s 2025 report.

Attacking AI - Jason Haddix - NDC Security 2026
AI-driven, large-scale nation-state campaign using ARTEX enables supply chain compromise | Microsoft Security Blog
Storm-0940 used ARTEX agentic AI to accelerate a ConnectWise supply chain compromise, enabling application credential abuse across Microsoft 365 environments.

AI-powered hacking has exploded into industrial-scale threat, Google says
Criminal groups and state-linked actors appear to be using commercial models to refine and scale up attacks

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete security impact, such as unauthorized file access or code execution. Exploitation is a particularly challenging task because it requires low-level program reasoning (e.g., about memory layout), runtime adaptation, and sustained progress over long horizons. Meanwhile, it is inherently dual-use, supporting defensive workflows while lowering the barrier for offense. Despite its importance and diagnostic value, exploitation remains under-evaluated. To address this gap, we introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents. Given a program input that triggers a vulnerability, ExploitGym tasks agents with progressively extending it into a working exploit. The benchmark comprises 898 instances sourced from real-world vulnerabilities across three domains, including userspace programs, Google's V8 JavaScript engine, and the Linux kernel. We vary the security protections applied to each instance, isolating their impact on agent performance. All configurations are packaged in reproducible containerized environments. Our evaluation shows that while exploitation remains challenging, frontier models can successfully exploit a non-trivial fraction of vulnerabilities. For example, the strongest configurations are Anthropic's latest model Claude Mythos Preview and OpenAI's GPT-5.5, which produce working exploits for 157 and 120 instances, respectively. Notably, even with widely used defenses enabled, models retain non-trivial success rates. These results establish ExploitGym as an effective testbed for exploitation and highlight the growing cybersecurity risks posed by increasingly capable AI agents.

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete security impact, such as unauthorized file access or code execution. Exploitation is a particularly challenging task because it requires low-level program reasoning (e.g., about memory layout), runtime adaptation, and sustained progress over long horizons. Meanwhile, it is inherently dual-use, supporting defensive workflows while lowering the barrier for offense. Despite its importance and diagnostic value, exploitation remains under-evaluated. To address this gap, we introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents. Given a program input that triggers a vulnerability, ExploitGym tasks agents with progressively extending it into a working exploit. The benchmark comprises 898 instances sourced from real-world vulnerabilities across three domains, including userspace programs, Google's V8 JavaScript engine, and the Linux kernel. We vary the security protections applied to each instance, isolating their impact on agent performance. All configurations are packaged in reproducible containerized environments. Our evaluation shows that while exploitation remains challenging, frontier models can successfully exploit a non-trivial fraction of vulnerabilities. For example, the strongest configurations are Anthropic's latest model Claude Mythos Preview and OpenAI's GPT-5.5, which produce working exploits for 157 and 120 instances, respectively. Notably, even with widely used defenses enabled, models retain non-trivial success rates. These results establish ExploitGym as an effective testbed for exploitation and highlight the growing cybersecurity risks posed by increasingly capable AI agents.

ARTEX in the Wild: Storm-0940 Expands Targeting of IT and Software Vendors | Wiz Blog
Wiz Research is tracking an ARTEX-using actor, overlapping with Storm-0940, across multiple targeted software vendors. Learn how the AI agent attacks Okta, Entra, and Cognito, and what it left behind in the logs.

AI CVE Slop: The Crisis Drowning Open Source Security
The proliferation of AI-generated vulnerability reports — commonly termed “AI slop” — has emerged as one of the most significant…
AI’s Hacking Skills Are Approaching an ‘Inflection Point’
AI models are getting so good at finding vulnerabilities that some experts say the tech industry might need to rethink how software is built.

AI Is Reshaping Hacking. No One Agrees How Fast - Slashdot
"Several cybersecurity companies debuted advancements in AI agents at the Black Hat conference last week," reports Axios, "signaling that cyber defenders could soon have the tools to catch up to adversarial hackers." - Microsoft shared details about a prototype for a new agent that can automaticall...

Hackers build AI frameworks for widescale credential theft
Threat actors are increasingly switching from AI-powered coding assistants to multi-agent frameworks that automate every stage of an attack.

Codex Security: now in research preview
Codex Security is an AI application security agent that analyzes project context to detect, validate, and patch complex vulnerabilities with higher confidence and less noise.

Forget the AI Slowdown—the Vulnerability Explosion Is Already Happening
AI labs are toying with an industry-wide pact to slow development. Meanwhile, widely available AI chatbots are already helping uncover a tidal wave of security flaws.

Prompt Injection Attacks Are Thwarting AI Hacking Agents
“Context bombing” tricks malicious AI agents into shutting down before they can do harm.

AI Agents Enable Adaptive Computer Worms
A computer worm is malware that spreads on a network by replicating itself from one machine to another. Traditional worms, like WannaCry, exploited predetermined vulnerabilities, and their spread can be halted by patching those vulnerabilities. Here we show that artificial intelligence (AI) agents enable a fundamentally new threat: a worm that generates tailored attack strategies to each target it encounters. The worm parasitically uses compromised machines to run open-weight large language models (LLMs) to sustain its reasoning, or extend its reach for further attacks. Deployed on a network of machines spanning Linux, Windows, and IoT (Internet of Things) devices, the worm propagated by exploiting common, real-world corporate network vulnerabilities. Since the worm is powered by stolen compute, the attacker's marginal cost per new infection is zero. This creates a destabilizing economic asymmetry between attackers and defenders. Moreover, because the worm requires no commercial AI platform, centralized safety controls, such as service refusals or rate limiting, are structurally irrelevant. Our results demonstrate that self-sustaining AI-driven cyber-threats are no longer theoretical. We must prepare for autonomous generative adversaries: malware systems that propagate without human operators and are defined not by fixed exploit code, but by the capacity to reason about targets, adapt to observations, and synthesize attack logic in real time.
