139 matches found
TeamPCP Used Mini Shai-Hulud Worm to Poison Over 400 npm and PyPI Packages
Research reveals that TeamPCP hijacked OIDC tokens to poison hundreds of TanStack, Mistral AI, and UiPath packages with the self-propagating Mini Shai-Hulud worm...
Mini Shai-Hulud Worm Compromises TanStack, Mistral AI, Guardrails AI & More Packages
TeamPCP , the threat actor behind the recentsupply chain attack spree, has been linked to the compromise of the npm and PyPI packages from TanStack, UiPath, Mistral AI, OpenSearch, and Guardrails AI as part of a fresh Mini Shai-Hulud campaign. The affected npm packages have been modified to inclu...
Attention Is Where You Attack
Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain poorly understood. We introduce the Attention Redistribution Attack ARA, a white-box adversarial attack that identifies...
The Mistral–Koyeb Deal and the Shift Toward Architectural Maturity in AI
...
Analysis of LLMs against Prompt Injection and Jailbreak Attacks
Large Language Models LLMs are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus,...
Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
Jailbreaking large language models LLMs has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit restricted or unsafe outputs, a phenomenon commonly referred to as...
Emoji-Based Jailbreaking of Large Language Models
Large Language Models LLMs are integral to modern AI applications, but their safety alignment mechanisms can be bypassed through adversarial prompt engineering. This study investigates emoji-based jailbreaking, where emoji sequences are embedded in textual prompts to trigger harmful and unethical...
Debian dla-4392 : python3-mistral-dashboard - security update
The remote Debian 11 host has a package installed that is affected by a vulnerability as referenced in the dla-4392 advisory. ------------------------------------------------------------------------- Debian LTS Advisory DLA-4392-1 [email protected] https://www.debian.org/lts/security/...
[SECURITY] [DLA 4392-1] mistral-dashboard security update
Debian LTS Advisory DLA-4392-1 [email protected] https://www.debian.org/lts/security/ Daniel Leidert December 01, 2025 https://wiki.debian.org/LTS Package : mistral-dashboard Version : 11.0.0-2+deb11u1 CVE ID : CVE-2021-4472 A local file inclusion vulnerability has been discovered in...
DLA-4392-1 mistral-dashboard - security update
Bulletin has no description...
Linux Distros Unpatched Vulnerability : CVE-2021-4472
The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - The mistral-dashboard plugin for openstack has a local file inclusion vulnerability through the 'Create Workbook' feature that may result in disclosure of...
Debian: Security Advisory (DLA-4392-1)
The remote host is missing an update for the Debian SPDX-FileCopyrightText: 2025 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...
DLA-4391-1 python-mistralclient - security update
Bulletin has no description...
SUSE CVE-2021-4472
The mistral-dashboard plugin for openstack has a local file inclusion vulnerability through the 'Create Workbook' feature that may result in disclosure of arbitrary local files content...
Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities
Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models LLMs present promising capabilities for automating this task. However, existing research has primarily assessed LLMs using publicly disclosed vulnerabilities, leaving their...
GHSA-75HX-6R6J-HW56 OpenStack's Mistral Client has a local file inclusion vulnerability
The mistral-dashboard plugin for openstack has a local file inclusion vulnerability through the 'Create Workbook' feature that may result in disclosure of arbitrary local files content...
EUVD-2021-34723
The mistral-dashboard plugin for openstack has a local file inclusion vulnerability through the 'Create Workbook' feature that may result in disclosure of arbitrary local files content...
OpenStack's Mistral Client has a local file inclusion vulnerability
The mistral-dashboard plugin for openstack has a local file inclusion vulnerability through the 'Create Workbook' feature that may result in disclosure of arbitrary local files content...
