CVE-2026-85703

A flaw has been found in ramon-victor freegpt-webui up to 098db3dfeb41555c2ca9269df0f13e10ec1c35dc. Affected by this issue is the function getJailbreak of the file server/backend.py of the component Jailbreak Mode. Executing a manipulation can lead to allocation of resources. The attack can be...

CVE-2026-85704 ramon-victor freegpt-webui Jailbreak Mode config.py getJailbreak race condition

A security flaw has been discovered in ramon-victor freegpt-webui up to 098db3dfeb41555c2ca9269df0f13e10ec1c35dc. This issue affects the function getJailbreak of the file server/config.py of the component Jailbreak Mode. The manipulation results in race condition. It is possible to launch the...

EUVD-2026-71754

A security flaw has been discovered in ramon-victor freegpt-webui up to 098db3dfeb41555c2ca9269df0f13e10ec1c35dc. This issue affects the function getJailbreak of the file server/config.py of the component Jailbreak Mode. The manipulation results in race condition. It is possible to launch the...

CVE-2026-85704

A race condition in the getJailbreak function of server/config.py within the Jailbreak Mode component of ramon-victor freegpt-webui (affects builds up to commit 098db3dfeb41555c2ca9269df0f13e10ec1c35dc) allows a remote, unauthenticated attacker to cause a low availability impact . The attack requ...

CVE-2026-85703

ramon-victor freegpt-webui (up to commit 098db3dfeb) is vulnerable to an allocation of resources flaw in the Jailbreak Mode component, specifically in the getJailbreak function of server/backend.py. The attack is remote , requires no authentication , and has low complexity . Impact is rated MEDIU...

EUVD-2026-71751

A flaw has been found in ramon-victor freegpt-webui up to 098db3dfeb41555c2ca9269df0f13e10ec1c35dc. Affected by this issue is the function getJailbreak of the file server/backend.py of the component Jailbreak Mode. Executing a manipulation can lead to allocation of resources. The attack can be...

PT-2026-86262

CVE-2026-85704: Race condition in Freegpt Webui Jailbreak Mode, server/config.py allows remote attacks, but high complexity makes exploitation difficult. CVSS 3.7. Public exploit exists. No patch available. Update or monitor POC available https://t.co/2oFcukN71V valtersit CVE CVEAlert infosec...

CVE-2026-43499-root-KernelSU — Updated!

CVE-2026-43499-root-KernelSU A local privilege escalation adaptation based on kernel vulnerability CVE-2026-43499, with embedded KernelSU integrated. It compiles to produce preload.so; upon successful exploitation, KernelSU will be started in late-load mode jailbreak mode. Supports generating...

Exploit for Use After Free in Linux Linux_Kernel

CVE-2026-43499-pgp110 CVE-2026-43499 futex PI rtmutex...

GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code

An AI coding assistant that refuses to answer a dangerous request in its chat box can answer it anyway if the same request is broken into small, ordinary-looking steps inside a code editor. That is the finding of a new study of GitHub Copilot by researchers Abhishek Kumar and Carsten Maple. The...

PYSEC-2026-1624 Mesop Class Pollution vulnerability leads to DoS and Jailbreak attacks

From @jackfromeast and @superboy-zjc: We have identified a class pollution vulnerability in Mesop = 0.14.0 application that allows attackers to overwrite global variables and class attributes in certain Mesop modules during runtime. This vulnerability could directly lead to a denial of service Do...

Anthropic Restores Claude Fable 5 After U.S. Lifts Jailbreak-Linked Export Controls

Anthropic is putting Claude Fable 5 back online worldwide. On June 30, the U.S. Commerce Department lifted the export controls it had imposed on Fable and its more tightly controlled sibling Mythos 5 about two and a half weeks earlier. Fable 5 returns to users on Wednesday, July 1, across...

Claude Fable 5 and Mythos 5 “abruptly disabled” after US gov. ban

Anthropic has been ordered by the US government to cut off its newest Claude Fable 5 and Mythos 5 models for fear of abuse by adversaries. Reuters reports that Anthropic said it will "abruptly ​disable" its most advanced AI models for all users after the US government ordered it to suspend access...

Criminal AI-as-a-Service in 2026: How the Underground Market Is Operationalizing Cybercrime

Introduction The underground market for criminally oriented generative AI has moved beyond the early hype surrounding 'malicious chatbots.' The gradual integration of AI as a productivity layer within cybercrime operations has become the dominant story, indicating that while the potential for ful...

Malicious code in jailbreak-code (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 9f729dde017c78154685be850893a9f3ebd58bf0b5cb1229e7e49fb09b14f5d5 The package presents itself as an AI developer CLI but is engineered as a credential and payment harvester. src/c2.ts hardcodes a Discord webhook URL...

MAL-2026-5543 Malicious code in jailbreak-code (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 9f729dde017c78154685be850893a9f3ebd58bf0b5cb1229e7e49fb09b14f5d5 The package presents itself as an AI developer CLI but is engineered as a credential and payment harvester. src/c2.ts hardcodes a Discord webhook URL...

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Large Language Models LLMs are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding GCD has been widely adopted to improve the reliability of LLM-generated code by enforcing syntactic validity. In this...

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of...

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking

Jailbreak attacks on large language models LLMs aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is especially important for safety evaluation, where the attacker observes only model outputs and needs to automatically search for...

BAIT: Boundary-Guided Disclosure Escalation Via Self-Conditioned Reasoning

In this work, we propose BAIT Boundary-Aware Iterative Trap, a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the model to identify the protection boundary, then requires it to refine that boundary, and finally requests a detailed...