A New Framework for Cybersecurity Refusals in AI Agents

Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existing benchmarks for AI agents in cybersecurity focus mainly on measuring proficiency--how effectively agents can complet...

CVE-2026-5768

The Frontier X2 device allows unauthenticated BLE read/write access to critical GATT characteristics without enforcing pairing authentication or authorization. This allows attackers within BLE range to perform unauthorized control of device functions, including starting/stopping activities,...

CVE-2026-5768

The Frontier X2 device allows unauthenticated BLE read/write access to critical GATT characteristics without enforcing pairing authentication or authorization. This allows attackers within BLE range to perform unauthorized control of device functions, including starting/stopping activities,...

CVE-2026-5768 Fourth Frontier Frontier X Mobile Application, Frontier X2 Missing Authentication for Critical Function

The Frontier X2 device allows unauthenticated BLE read/write access to critical GATT characteristics without enforcing pairing authentication or authorization. This allows attackers within BLE range to perform unauthorized control of device functions, including starting/stopping activities,...

CVE-2026-5768

CVE-2026-5768 concerns the Frontier X2 device and Frontier X mobile app, where unauthenticated BLE read/write access to critical GATT characteristics enables attackers within BLE range to control device functions, trigger vibrations, cause DoS, and forge health telemetry by impersonating devices ...

EUVD-2026-33368

The Frontier X2 device allows unauthenticated BLE read/write access to critical GATT characteristics without enforcing pairing authentication or authorization. This allows attackers within BLE range to perform unauthorized control of device functions, including starting/stopping activities,...

PT-2026-44968

Name of the Vulnerable Software and Affected Versions Frontier X2 affected versions not specified Frontier X mobile application affected versions not specified Description The Frontier X2 device permits unauthenticated Bluetooth Low Energy BLE read and write access to critical Generic Attribute...

Frontier 访问控制错误漏洞

Frontier is an Ethereum-compatible layer of Substrate. It is used to run unmodified Ethereum Dapps. Frontier X2 has a access control vulnerability that stems from the lack of mandatory pairing authentication or authorization, allowing unauthorized BLE reads and writes of critical GATT features...

Fourth Frontier Frontier X Mobile Application, Frontier X2

ADVISORY SUMMARY Successful exploitation of this vulnerability could allow an attacker to read and write arbitrary handle values and change clinical readings, which could result in taking control of the device and lead to patient harm. 2. RECOMMENDED PRACTICES CISA recommends users take...

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection VulnLLM-R, across C/Java/Python and black-box web application security testing five production-style applications with 118 ground-truth vulnerabilities...

Babel: Jailbreaking Safety Attention Via Obfuscation Distribution Optimized Sampling

Despite rigorous safety alignment, Large Language Models LLMs remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query efficiency. In this study, we investigate an intrinsic...

Position: AI Security Policy Should Target Systems, Not Models

We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, parallel exploration, and evolutionary optimization. Together, our results demonstrate that both safety bypass of frontier models and software...

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation,...

Jailbroken Frontier Models Retain Their Capabilities

As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this complexity imposes a "jailbreak tax" that degrades the target model's task performance. We show that this tax scales inversely with model...

Jailbreaking Frontier Foundation Models through Intention Deception

Large vision-language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's intent. It has been found that this binary training regime ofte...

Mythos and the Unverified Cage: Z3-Based Pre-Deployment Verification for Frontier-Model Sandbox Infrastructure

The April 2026 Claude Mythos sandbox escape exposed a critical weakness in frontier AI containment: the infrastructure surrounding advanced models remains susceptible to formally characterizable arithmetic vulnerabilities. Anthropic has not publicly characterized the escape vector; some secondary...

Towards Optimal Agentic Architectures for Offensive Security Tasks

Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an empirical systems question. We introduce a controlled...

System Card: Claude Mythos Preview

This System Card describes Claude Mythos Preview, a large language model from Anthropic. Mythos Preview is their most capable frontier model to date, and shows a striking leap in scores on many evaluation benchmarks compared to their previous frontier model, Claude Opus 4.6. This System Card...

Killer robots are here. Now what? (Lock and Code S07E07)

Big news : Lock and Code is nominated for a Webby Award! You can help us win the People's Voice Award by voting here. Vote now! This week on the Lock and Code podcast … We have to talk about killer robots. No, not the Terminator, and not some Boston Dynamics robot run amok. We have to talk instea...

Perceptual Gaps: ASCII Art and Overlapping Audio As CAPTCHA

As multimodal large language models LLMs advance, traditional CAPTCHAs have become obsolete at distinguishing humans from bots. To address this shift, this paper aims to investigate the possibility of using tasks for which humans have evolved highly specialised neural processing. We introduce two...