Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors

Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed as a privacy boundary, we reveal that compromised model code is sufficient to steal them. Current passive...

security-audit

security-audit A Claude Code skill + plugin marketplace for a...

UNC6692 Impersonates IT Help Desk via Microsoft Teams to Deploy SNOW Malware

A previously undocumented threat activity cluster known as UNC6692 has been observed leveraging social engineering tactics via Microsoft Teams to deploy a custom malware suite on compromised hosts. "As with many other intrusions in recent years, UNC6692 relied heavily on impersonating IT help des...

AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models

Automated red-teaming methods for large language models typically optimize attack prompts within a fixed, human-designed strategy, leaving the attack strategy itself unchanged. We instead optimize the strategy. We propose AutoRISE, a method that searches over executable attack programs rather tha...

OpenMcdf has an Infinite loop DoS via crafted CFB directory cycle

Summary OpenMcdf does not detect cycles in the directory entry red-black tree of a Compound File Binary CFB document. A crafted CFB file with a cycle in the LeftSiblingID / RightSiblingID chain causes Storage.EnumerateEntries and Storage.OpenStream to loop indefinitely, consuming the calling thre...

Unity Linux 20.1050e / 20.1070e Security Update: kernel (UTSA-2026-011349)

"The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2026-011349 advisory. In the Linux kernel, the following vulnerability has been resolved: fs/proc: fix uaf in procreaddirde Pde is erased from subdir rbtree through rberase, but not set...

Unity Linux 20.1070a Security Update: kernel (UTSA-2026-013099)

"The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2026-013099 advisory. In the Linux kernel, the following vulnerability has been resolved: fs/proc: fix uaf in procreaddirde Pde is erased from subdir rbtree through rberase, but not set...

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...

ThreatsDay Bulletin: Hybrid P2P Botnet, 13-Year-Old Apache RCE and 18 More Stories

Thursday. Another week, another batch of things that probably should've been caught sooner but weren't. This one's got some range — old vulnerabilities getting new life, a few "why was that even possible" moments, attackers leaning on platforms and tools you'd normally trust without thinking twic...

Malicious code in black-moon-js (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 7c672e4ab8770773551a9ff9b6b95a5740894bd1c689154056f69e5da4fdb879 The package black-moon-js was found to contain malicious code. Source: ossf-package-analysis...

MAL-2026-2870 Malicious code in black-moon-js (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 7c672e4ab8770773551a9ff9b6b95a5740894bd1c689154056f69e5da4fdb879 The package black-moon-js was found to contain malicious code. Source: ossf-package-analysis...

Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses under White-Box and Black-Box Threats

Concept drift and adversarial evasion are two major challenges for deploying machine learning-based malware detectors. While both have been studied separately, their combination, the adversarial robustness of drift-adaptive detectors, remains unexplored. We address this problem with AdvDA, a rece...

Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning

Large language models LLMs possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models LRMs, which provide explicit multi-step reasoning traces. On the other hand, the growing need for the right to be forgotte...

SUSE: Security Advisory (SUSE-SU-2026:20928-1)

The remote host is missing an update for the SPDX-FileCopyrightText: 2026 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...

Blazing-Black-Dragon

No d...

AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications

Large-scale web applications are widely deployed with complex third-party components, inheriting security risks arising from component vulnerabilities. Security assessment is therefore required to determine whether such known vulnerabilities remain practically exploitable in real applications...

openSUSE 16 Security Update : python-black (openSUSE-SU-2026:20417-1)

The remote openSUSE 16 host has a package installed that is affected by multiple vulnerabilities as referenced in the openSUSE-SU-2026:20417-1 advisory. - CVE-2026-31900: a malicious pyproject.toml edit can lead to arbitrary code execution bsc1259546. - CVE-2026-32274: arbitrary file writes from...

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation

The emergence of Large Language Model-enhanced Search Engines LLMSEs has revolutionized information retrieval by integrating web-scale search capabilities with AI-powered summarization. While these systems demonstrate improved efficiency over traditional search engines, their security implication...

OPENSUSE-SU-2026:20417-1 Security update for python-black

This update for python-black fixes the following issues: - CVE-2026-31900: a malicious pyproject.toml edit can lead to arbitrary code execution bsc1259546. - CVE-2026-32274: arbitrary file writes from unsanitized user input in cache file name bsc1259608...

WordPress JupiterX Core plugin <= 4.14.1 - Authenticated (Subscriber+) Missing Authorization To Limited File Upload via Popup Template Import vulnerability

Authenticated Subscriber+ Missing Authorization To Limited File Upload via Popup Template Import vulnerability discovered by Jack Pas Dark. - Black Lantern Security in WordPress Plugin JupiterX Core versions = 4.14.1...