OpenAI Launches GPT-5.4-Cyber with Expanded Access for Security Teams

OpenAI on Tuesday unveiled GPT-5.4-Cyber , a variant of its latest flagship model, GPT‑5.4, that's specifically optimized for defensive cybersecurity use cases, days after rival Anthropic unveiled its own frontier model, Mythos. "The progressive use of AI accelerates defenders – those responsible...

coruna-exploit-kit-analysis

Coruna iOS Exploit Kit — Reverse Engineering Analysis Def...

cybersentinel-agent

CyberSentinel Agent Defensive cybersecurity agent framework w...

System Card: Claude Mythos Preview

This System Card describes Claude Mythos Preview, a large language model from Anthropic. Mythos Preview is their most capable frontier model to date, and shows a striking leap in scores on many evaluation benchmarks compared to their previous frontier model, Claude Opus 4.6. This System Card...

Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on approximately 10,000 trials across seven models, 37 prompt...

redhound-arsenal

Red Hound Arsenal Agent-consumable security skill library for...

AARTF---Autonomous-AI-RedTeam-Framework

AARTF AI-Driven Autonomous Security Workflow !CIhttps:/...

Anritsu Remote Spectrum Monitor

RISK EVALUATION Successful exploitation of this vulnerability could allow attackers with network access to alter operational settings, obtain sensitive signal data, or disrupt device availability. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of...

OC Messaging and Custom Messaging Gateway

RISK EVALUATION Successful exploitation of this vulnerability could allow an authenticated low-privileged user to gain access to SMS messages outside of their authorized tenant scope via a crafted company or tenant identifier parameter. 2. RECOMMENDED PRACTICES CISA recommends users take...

PTC Windchill Product Lifecycle Management

RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker to achieve remote code execution. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of this vulnerability. Minimize network exposure for all control...

ide-task-rce

⚡ IDE Folder-Open RCE: Automatic Task Execution Vulnerability...

SoK: The Attack Surface of Agentic AI -- Tools, and Autonomy

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation RAG, and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we m...

Case study: How predictive shielding in Defender stopped GPO-based ransomware before it started

In this article 1. The growing threat: GPO abuse in ransomware operations 2. The incident 3. The results 4. The hardening dilemma: Why threat actors love operational mechanisms 5. Predictive shielding: Contextual, just-in-time hardening 6. Closing the gap 7. References Summary Microsoft Defender...

Exploit for CVE-2025-9074

Description Vibe coded a small exploit script in pure Bash wit...

cyberops-security-suite

CyberOps Security Suite A comprehensive cybersecurity operati...

Automated Logic WebCTRL Premium Server

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to read, intercept, or modify communications. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these vulnerabilities, such as: Minimize network...

Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive comparative security assessment exists across major LLM...

Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents

OpenClaw-like agents offer substantial productivity benefits, yet they are insecure by default because they combine untrusted inputs, autonomous action, extensibility, and privileged system access within a single execution loop. We use OpenClaw as an exemplar of a broader class of agents that...

📄 Microsoft Windows LNK File Remote Code Execution

This PHP script is a proof of concept exploit that demonstrates how to create a Windows LNK shortcut file that executes a PowerShell command in this example, launches calc.exe...

VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

As Large Vision-Language Models LVLMs are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignment is typically tested on explicit harmful content rather than privacy-critical...