Memory Poisoning Attack and Defense on Memory Based LLM-Agents

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence future responses. Recent work demonstrated that the MINJA...

CVE-2026-21683

iccDEV provides a set of libraries and tools that allow for the interaction, manipulation, and application of International Color Consortium ICC color management profiles. Versions prior to 2.3.1.2 have a Type Confusion vulnerability in icStatusCMM::CIccEvalCompare::EvaluateProfile. This...

CVE-2022-27123

Employee Performance Evaluation v1.0 was discovered to contain a SQL injection vulnerability via the email parameter...

CVE-2019-16554

A missing permission check in Jenkins Build Failure Analyzer Plugin 1.24.1 and earlier allows attackers with Overall/Read permission to have Jenkins evaluate a computationally expensive regular expression...

Important: amazon-cloudwatch-agent

Issue Overview: SSH Agent servers do not validate the size of messages when processing new identity requests, which may cause the program to panic if the message is malformed due to an out of bounds read. CVE-2025-47914 SSH servers parsing GSSAPI authentication requests do not validate the number...

Jailbreaking LLMs and VLMs: Mechanisms, Evaluation, and Unified Defense

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models LLMs and Vision-Language Models VLMs, emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training data, linguistic ambiguity, and generative uncertainty. It...

RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models

As large language models LLMs become integral to safety-critical applications, ensuring their robustness against adversarial prompts is paramount. However, existing red teaming datasets suffer from inconsistent risk categorizations, limited domain coverage, and outdated evaluations, hindering...

A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-Case Prototypes

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these systems enable continuous, autonomous workflows in real-world...

expr-eval: expr-eval: Prototype Pollution

A prototype pollution flaw was found in expr-eval. An attacker with access to express eval interface can use JavaScript prototype-based inheritance model to achieve arbitrary code execution...

LLMs, You Can Evaluate It! Design of Multi-Perspective Report Evaluation for Security Operation Centers

Security operation centers SOCs often produce analysis reports on security incidents, and large language models LLMs will likely be used for this task in the near future. We postulate that a better understanding of how veteran analysts evaluate reports, including their feedback, can help produce...

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

The rapid integration of Multimodal Large Language Models MLLMs into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to single-turn text interactions, and lack the scalability required for...

SQLi_AI_defence

SQLiAIdefence A small model ba...

EUVD-2026-0130

This CVE ID was rejected because it was reserved but not used for a vulnerability disclosure...

Remote Code Execution (RCE)

n8n is vulnerable to Remote Code Execution RCE. The vulnerability is due to insufficient isolation in the workflow expression evaluation system, which allows an authenticated attacker to supply crafted expressions that are executed in the runtime context, enabling arbitrary code execution with th...

Beyond Single Bugs: Benchmarking Large Language Models for Multi-Vulnerability Detection

Large Language Models LLMs have demonstrated significant potential in automated software security, particularly in vulnerability detection. However, existing benchmarks primarily focus on isolated, single-vulnerability samples or function-level classification, failing to reflect the complexity of...

EUVD-2025-204970

Tencent TFace eval Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Tencent TFace. User interaction is required to exploit this vulnerability in that the target must visit a...

AutoBaxBuilder: Bootstrapping Code Security Benchmarking

As LLMs see wide adoption in software engineering, the reliable assessment of the correctness and security of LLM-generated code is crucial. Notably, prior work has demonstrated that security is often overlooked, exposing that LLMs are prone to generating code with security vulnerabilities. These...

AlmaLinux 9 : opentelemetry-collector (ALSA-2025:23729)

The remote AlmaLinux 9 host has a package installed that is affected by a vulnerability as referenced in the ALSA-2025:23729 advisory. github.com/expr-lang/expr: Expr: Denial of Service via uncontrolled recursion in expression evaluation CVE-2025-68156 Tenable has extracted the preceding...

CVE-2025-13711

CVE-2025-13711 affects Tencent TFace, specifically the eval endpoint. The root cause is improper validation that enables deserialization of untrusted data, leading to remote code execution. Exploitation requires user interaction (visiting a malicious page or opening a malicious file); successful ...

opentelemetry-collector security update

An update is available for opentelemetry-collector. This update affects Rocky Linux 9. A Common Vulnerability Scoring System CVSS base score, which gives a detailed severity rating, is available for each vulnerability from the CVE list Collector with the supported components for a Rocky Enterpris...