Updated thunderbird packages fix security vulnerabilities

Incorrect boundary conditions in the WebRTC: Audio/Video component. CVE-2026-2757 Use-after-free in the JavaScript: GC component. CVE-2026-2758 Incorrect boundary conditions in the Graphics: ImageLib component. CVE-2026-2759 Sandbox escape due to incorrect boundary conditions in the Graphics:...

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal safeguards to mitigate harmful behavior. Prior red-teaming research has largel...

CVE-2019-20713

Certain NETGEAR devices are affected by a stack-based buffer overflow by an authenticated user. This affects D8500 before 1.0.3.44, R6250 before 1.0.4.34, R6300v2 before 1.0.4.32, R6400 before 1.0.1.46, R6700 before 1.0.2.6, R6900 before 1.0.2.4, R6900P before 1.3.1.64, R7000 before 1.0.9.42,...

CVE-2017-18756

Certain NETGEAR devices are affected by incorrect configuration of security settings. This affects D6220 before 1.0.0.32, D6400 before 1.0.0.66, D8500 before 1.0.3.35, DGN2200Bv4 before 1.0.0.94, DGN2200v4 before 1.0.0.94, R6250 before 1.0.4.14, R6300v2 before 1.0.4.18, R6400 before 1.01.32,...

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models

Large Language Models LLMs face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined by several critical limitations: they struggle to maintain ...

Jailbreaking in the Haystack

Recent advances in long-context language models LMs have enabled million-token inputs, expanding their capabilities across complex tasks like computer-use agents. Yet, the safety implications of these extended contexts remain unclear. To bridge this gap, we introduce NINJA short for...

EUVD-2018-13731

Malware in sbrugna...

EUVD-2022-46565

Malicious code in bioql PyPI...

LLM Detected

The scanner detected the presence of a Large Language Model LLM on the target application. LLMs are advanced AI models capable of understanding and generating human-like text based on the input they receive. They are commonly used in various applications, including chatbots, virtual assistants,...

PT-2025-31846 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server versions affected versions not specified Description: NVIDIA Triton Inference Server for Windows and Linux contains an issue in the Python backend. An attacker could exceed the shared memory limit by sending a...

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques

Large Language Models LLMs are transforming cybersecurity by enabling intelligent, adaptive, and automated approaches to threat detection, vulnerability assessment, and incident response. With their advanced language understanding and contextual reasoning, LLMs surpass traditional methods in...

Recalling the Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy

Machine Unlearning MU technology facilitates the removal of the influence of specific data instances from trained models on request. Despite rapid advancements in MU technology, its vulnerabilities are still under explored, posing potential risks of privacy breaches through leaks of ostensibly...

ATAG: AI-Agent Application Threat Assessment with Attack Graphs

Evaluating the security of multi-agent systems MASs powered by large language models LLMs is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack graph AG methods often lack the specific capabilities to model...

CVE-2020-35813

Certain NETGEAR devices are affected by stored XSS. This affects D7800 before 1.0.1.56, RBK50 before 2.3.5.30, RBR50 before 2.3.5.30, RBS50 before 2.3.5.30, RBK40 before 2.3.5.30, RBR40 before 2.3.5.30, RBS40 before 2.3.5.30, RBK20 before 2.3.5.26, RBR20 before 2.3.5.26, RBS20 before 2.3.5.26,...

Applying Security Engineering to Prompt Injection Security

This seems like an important advance in LLM security against prompt injection: Google DeepMind has unveiled CaMeL CApabilities for MachinE Learning, a new approach to stopping prompt-injection attacks that abandons the failed strategy of having AI models police themselves. Instead, CaMeL treats...

NIST Warns of Security and Privacy Risks from Rapid AI System Deployment

The U.S. National Institute of Standards and Technology NIST is calling attention to the privacy and security challenges that arise as a result of increased deployment of artificial intelligence AI systems in recent years. "These security and privacy challenges include the potential for adversari...