Securing Large Language Models (LLMs) from Prompt Injection Attacks

Large Language Models LLMs are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform malicious tasks. Recent work has proposed JATMO, a task-specif...

delve and golang security update

delve 1.25.2-1.0.1 - Disable DWARF compression which has issues Alex Burmashev 1.25.2-1 - Update to Delve 1.25.2 - Resolves: RHEL-111801 golang 1.25.3-1 - Update to Go 1.25.3 - Resolves: RHEL-121220 1.25.1-1 - Update to Go 1.25.1 - Resolves: RHEL-116850 1.25.0-2 - Revert DWARF5 defaults - Add elf...

Malicious Package

Overview baseline-server is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...

Astra Linux – Vulnerability in Firefox and Thunderbird

On 64-bit platforms, IonMonkey-JIT only writes 32 bits of the 64-bit return value space onto the stack. However, Baseline-JIT reads the entire 64 bits. This vulnerability was fixed in Firefox 141, Firefox ESR 115.26, Firefox ESR 128.13, Firefox ESR 140.1, Thunderbird 141, Thunderbird 128.13, and...

curl: curl built with GnuTLS backend defaults to weak crypto parameters

Summary: Curl configured with GnuTLS backend --with-gnutls defaults using "NORMAL" as the base level of the library cryptographic security. From GnuTLS documentation: The message authenticity security level is of 64 bits or more, and the certificate verification profile is set to GNUTLSPROFILELOW...

EUVD-2025-37319

Malicious code in baseline-server npm...

Malicious code in baseline-server (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6e8f0d63405c3006d5549ebf1df01f884df985fdbac7dfcc07c22c06ad556c8e The package baseline-server was found to contain malicious code. Source: ghsa-malware 2eef37dadfa82b7f47a185f272073322cc60a193be57b46387b84bbc55b3655...

MAL-2025-49303 Malicious code in baseline-server (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6e8f0d63405c3006d5549ebf1df01f884df985fdbac7dfcc07c22c06ad556c8e The package baseline-server was found to contain malicious code. Source: ghsa-malware 2eef37dadfa82b7f47a185f272073322cc60a193be57b46387b84bbc55b3655...

The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerability

Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically validate the Trust-Vulnerability Paradox TVP: increasing inter-agent trust to enhance coordination simultaneously expan...

EUVD-2005-4372

Malware in sbrugna...

EUVD-2005-4373

Malware in sbrugna...

EUVD-2002-1741

Malware in sbrugna...

Unity Linux 20.1070a Security Update: firefox (UTSA-2025-987437)

The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2025-987437 advisory. On 64-bit platforms IonMonkey-JIT only wrote 32 bits of the 64-bit return value space on the stack. Baseline-JIT, however, read the entire 64 bits. This vulnerabilit...

EUVD-2024-39185

Malicious code in bioql PyPI...

A Non-Monotonic Relationship: an Empirical Analysis of Hybrid Quantum Classifiers for Unseen Ransomware Detection

Detecting unseen ransomware is a critical cybersecurity challenge where classical machine learning often fails. While Quantum Machine Learning QML presents a potential alternative, its application is hindered by the dimensionality gap between classical data and quantum hardware. This paper...

The Aegis Protocol: a Foundational Security Framework for Autonomous AI Agents

The proliferation of autonomous AI agents marks a paradigm shift toward complex, emergent multi-agent systems. This transition introduces systemic security risks, including control-flow hijacking and cascading failures, that traditional cybersecurity paradigms are ill-equipped to address. This...

Malicious code in tslint-config-baseline (npm)

The package tslint-config-baseline was found to contain malicious code...

MAL-2025-37259 Malicious code in tslint-config-baseline (npm)

The package tslint-config-baseline was found to contain malicious code...

firefox: thunderbird: JavaScript engine only wrote partial return value to stack

A flaw was found in Firefox and Thunderbird. The Mozilla Foundation's Security Advisory describes the following issue: On 64-bit platforms, IonMonkey-JIT only wrote 32 bits of the 64-bit return value space on the stack. Baseline-JIT, however, reads the entire 64 bits...

firefox: thunderbird: JavaScript engine only wrote partial return value to stack

A flaw was found in Firefox and Thunderbird. The Mozilla Foundation's Security Advisory describes the following issue: On 64-bit platforms, IonMonkey-JIT only wrote 32 bits of the 64-bit return value space on the stack. Baseline-JIT, however, reads the entire 64 bits...