EUVD-2025-31171

Malicious code in bioql PyPI...

SoK: Measuring What Matters for Closed-Loop Security Agents

Cybersecurity is a relentless arms race, with AI driven offensive systems evolving faster than traditional defenses can adapt. Research and tooling remain fragmented across isolated defensive functions, creating blind spots that adversaries exploit. Autonomous agents capable of integrating, explo...

MAVUL: Multi-Agent Vulnerability Detection Via Contextual Reasoning and Interactive Refinement

The widespread adoption of open-source software OSS necessitates the mitigation of vulnerability risks. Most vulnerability detection VD methods are limited by inadequate contextual understanding, restrictive single-round interactions, and coarse-grained evaluations, resulting in undesired model...

Quant Fever, Reasoning Blackholes, Schrodinger'S Compliance, and More: Probing GPT-OSS-20B

OpenAI's GPT-OSS family provides open-weight language models with explicit chain-of-thought CoT reasoning and a Harmony prompt format. We summarize an extensive security evaluation of GPT-OSS-20B that probes the model's behavior under different adversarial conditions. Using the Jailbreak Oracle J...

CVE-2025-10975

A vulnerability was found in GuanxingLu vlarl up to 31abc0baf53ef8f5db666a1c882e1ea64def2997. This vulnerability affects the function experiments.robot.bridge.reasoningserver::runreasoningserver of the file experiments/robot/bridge/reasoningserver.py of the component ZeroMQ. Performing manipulati...

CVE-2025-10975

A vulnerability was found in GuanxingLu vlarl up to 31abc0baf53ef8f5db666a1c882e1ea64def2997. This vulnerability affects the function experiments.robot.bridge.reasoningserver::runreasoningserver of the file experiments/robot/bridge/reasoningserver.py of the component ZeroMQ. Performing manipulati...

CVE-2025-10975

A vulnerability was found in GuanxingLu vlarl up to 31abc0baf53ef8f5db666a1c882e1ea64def2997. This vulnerability affects the function experiments.robot.bridge.reasoningserver::runreasoningserver of the file experiments/robot/bridge/reasoningserver.py of the component ZeroMQ. Performing manipulati...

CVE-2025-10975 GuanxingLu vlarl ZeroMQ reasoning_server.py run_reasoning_server deserialization

A vulnerability was found in GuanxingLu vlarl up to 31abc0baf53ef8f5db666a1c882e1ea64def2997. This vulnerability affects the function experiments.robot.bridge.reasoningserver::runreasoningserver of the file experiments/robot/bridge/reasoningserver.py of the component ZeroMQ. Performing manipulati...

CVE-2025-10975 GuanxingLu vlarl ZeroMQ reasoning_server.py run_reasoning_server deserialization

A vulnerability was found in GuanxingLu vlarl up to 31abc0baf53ef8f5db666a1c882e1ea64def2997. This vulnerability affects the function experiments.robot.bridge.reasoningserver::runreasoningserver of the file experiments/robot/bridge/reasoningserver.py of the component ZeroMQ. Performing manipulati...

CVE-2025-10975

The CVE-2025-10975 entry concerns GuanxingLu vlarl up to version 31abc0baf53ef8f5db666a1c882e1ea64def2997. The vulnerability affects the function experiments.robot.bridge.reasoning_server::run_reasoning_server in experiments/robot/bridge/reasoning_server.py within the ZeroMQ component. The root c...

PT-2025-39459

Name of the Vulnerable Software and Affected Versions GuanxingLu vlarl versions prior to 31abc0baf53ef8f5db666a1c882e1ea64def2997 Description A flaw exists in the experiments.robot.bridge.reasoning server::run reasoning server function within the experiments/robot/bridge/reasoning server.py file ...

VLA-RL 代码问题漏洞

VLA-RL is a visual language action model by the individual developer of lgx. A code issue vulnerability exists in VLA-RL, which stems from misuse of the parameter Message in the file experiments/robot/bridge/reasoningserver.py, which could lead to a deserialization attack...

LLaVul: a Multimodal LLM for Interpretable Vulnerability Reasoning about Source Code

Increasing complexity in software systems places a growing demand on reasoning tools that unlock vulnerabilities manifest in source code. Many current approaches focus on vulnerability analysis as a classifying task, oversimplifying the nuanced and context-dependent real-world scenarios. Even...

Orion: Fuzzing Workflow Automation

Fuzz testing is one of the most effective techniques for finding software vulnerabilities. While modern fuzzers can generate inputs and monitor executions automatically, the overall workflow, from analyzing a codebase, to configuring harnesses, to triaging results, still requires substantial manu...

Guided Reasoning in LLM-Driven Penetration Testing Using Structured Attack Trees

Recent advances in Large Language Models LLMs have driven interest in automating cybersecurity penetration testing workflows, offering the promise of faster and more consistent vulnerability assessment for enterprise systems. Existing LLM agents for penetration testing primarily rely on self-guid...

All You Need Is a Fuzzing Brain: an LLM-Powered System for Automated Vulnerability Detection and Patching

Our team, All You Need Is A Fuzzing Brain, was one of seven finalists in DARPA's Artificial Intelligence Cyber Challenge AIxCC, placing fourth in the final round. During the competition, we developed a Cyber Reasoning System CRS that autonomously discovered 28 security vulnerabilities - including...

Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities

Traditional Artificial Intelligence AI approaches in cybersecurity exhibit fundamental limitations: inadequate conceptual grounding leading to non-robustness against novel attacks; limited instructibility impeding analyst-guided adaptation; and misalignment with cybersecurity objectives...

Reasoning Introduces New Poisoning Attacks yet Makes Them More Complicated

Early research into data poisoning attacks against Large Language Models LLMs demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reasoning, expanding the attack surface to include the intermediate chain-of-thought CoT and its inherent trait of...

VulRTex: a Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report

Software vulnerabilities exist in open-source software OSS, and the developers who discover these vulnerabilities may submit issue reports IRs to describe their details. Security practitioners need to spend a lot of time manually identifying vulnerability-related IRs from the community, and the...

Between a Rock and a Hard Place: Exploiting Ethical Reasoning to Jailbreak LLMs

Large language models LLMs have undergone safety alignment efforts to mitigate harmful outputs. However, as LLMs become more sophisticated in reasoning, their intelligence may introduce new security risks. While traditional jailbreak attacks relied on singlestep attacks, multi-turn jailbreak...