Understanding and Evaluating Claw-Like Agent Security through a Computer-Systems Lens

Claw-like AI agents e.g., OpenClaw are always-on processes with persistent access to credentials, files, tools, and external services. They take on system-level responsibilities -- installing packages, maintaining state, scheduling subtasks, and mediating I/O -- making security failures far more...

Forensic Trajectory Signatures for Agent Memory Poisoning Detection

We discover a behavioral invariant in LLM agents under persistent memory poisoning: in architectures where routing information is retrieved through observable memory-tool invocations, successful attacks require calling memoryrecallfact before emailsendemail, a transition that non-exfiltrating...

MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

Multi-agent systems MAS are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that remain poorly understood and are difficult to defend against. In this paper, we address how defenders should prioritize...

Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense

We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppressing untrusted text, which corrupts tasks that must preserve it, such as translation and document editing. Attack-success metrics cannot see this,...

AI-Generated PowerShell Malware: An Experimental Framework and Dataset

Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious purposes via scripting languages such as PowerShell. Consequently, for cybersecurity analysts, it is imperative to investigate the offensive...

Top Cyber Range Providers: A Comparison of 15 Leading Platforms

Compare 15 cyber range platforms across live-fire exercises, AI testing, SOC training, OT realism, deployment options, pricing models, and data residency needs...

An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models across Multilingual and Obfuscated Attack Scenarios

Large Language Models LLMs have rapidly evolved, transforming industries by automating complex tasks and generating human-like content. However, as their adoption accelerates, prompt injection vulnerabilities have become increasingly apparent. Malicious actors exploit these weaknesses to generate...

Missing Authentication For Critical Function

Backpropagate is vulnerable to Missing Authentication for Critical Function. The vulnerability is due to the Reflex web UI failing to enforce the --auth authentication mechanism despite indicating it is enabled, which allows an attacker who can access the exposed UI port to perform unauthorized...

Cybersecurity Is the True Frontier for Generative AI Success or Failure

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models LLMs to automate processes as "agents.'' Cybersecurity workflows require orchestrating hundreds of standard and bespoke tools through various...

FlipGuard: Defending Large Language Models against Quantization-Conditioned Backdoor Attacks

Model quantization is essential for the efficient deployment of Large Language Models LLMs, but introduces a critical vulnerability: Quantization-Conditioned Backdoor QCB attacks. In these attacks, malicious behaviors remain dormant in full-precision models and activate only after specific...

LLM Agents Security Duality: A Comprehensive Survey of Self-Security and Empowered Cybersecurity

Large language model LLM agents are rapidly being integrated into real-world systems. Their autonomy and tool-use capabilities generate substantial value while simultaneously expanding the security attack surface. This survey provides a comprehensive overview of the opportunities and challenges o...

Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs

CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD. We present the first empirical study of how DP SGD and HMAC pseudonymization interact when fine tuning...

CVE-2025-71340

picklescan through 0.0.26 fails to detect malicious pickle files that invoke idlelib.pyshell.ModifiedInterpreter.runcode in reduce methods. Attackers can embed undetected code in pickle files that executes arbitrary commands when the file is loaded via pickle.load, enabling supply chain attacks o...

CVE-2025-71340 picklescan - Remote Code Execution via idlelib.pyshell.ModifiedInterpreter.runcode

picklescan through 0.0.26 fails to detect malicious pickle files that invoke idlelib.pyshell.ModifiedInterpreter.runcode in reduce methods. Attackers can embed undetected code in pickle files that executes arbitrary commands when the file is loaded via pickle.load, enabling supply chain attacks o...

CVE-2025-71340

picklescan through 0.0.26 fails to detect malicious pickle files that invoke idlelib.pyshell.ModifiedInterpreter.runcode in reduce methods. Attackers can embed undetected code in pickle files that executes arbitrary commands when the file is loaded via pickle.load, enabling supply chain attacks o...

Beyond IOCs: AI-enabled threat intelligence

Welcome to this week's Threat Source newsletter. The issue of AI in cybersecurity is often portrayed as a binary choice: either a force multiplier for our adversaries, or a tool bringing professional obsolescence. The reality is more nuanced. While AI certainly brings some advantage to attackers,...

pentest-agent-vs-llm-benchmark-effectiveness

Backbone or Backbone-Architecture? A controlled study of LLM age...

Interesting Paper Exploring Prompt Injection

This is a fascinating explotation of how LLMs fall for prompt injection attacks. It turns out that they learn to recognize the style of text in different role/instruction blocks, and not just the tags. Their conclusion: Role tags were a formatting trick that became the security architecture and t...

Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions

We present a novel approach for applying Large Language Models LLMs to threat assessment in the context of foreign peacekeeping missions. Building on the PINPOINT project and its use case, the EU Monitoring Mission in Georgia, we combine an interdisciplinary risk-model with OSINT-based media...

Dawn of the Apex Agentic Adversary

We are standing at the end of an era we never thought to mourn: the era of human-speed threats. For years, cybersecurity moved to a rhythm organizations could follow. A researcher found a bug, a CVE was cataloged, a vendor navigated a patch cycle, and weeks or even months later, a fix was deploye...