shadowforge

ShadowForge "Trust no one. Suspect ev...

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of automation and powerful personalization, they also expose...

Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts

The deployment of large language models LLMs in Swiss financial and regulatory contexts demands empirical evidence of both production reliability and adversarial security, dimensions not jointly operationalized in existing Swiss-focused evaluation frameworks. This paper introduces Swiss-Bench 003...

Can Drift-Adaptive Malware Detectors Be Made Robust? Attacks and Defenses under White-Box and Black-Box Threats

Concept drift and adversarial evasion are two major challenges for deploying machine learning-based malware detectors. While both have been studied separately, their combination, the adversarial robustness of drift-adaptive detectors, remains unexplored. We address this problem with AdvDA, a rece...

Exploit for CVE-2025-1974

cve-2025-1974-win11-attack-defense-lab Windows 11-first educa...

SALLIE: Safeguarding against Latent Language and Image Exploits

Large Language Models LLMs and Vision-Language Models VLMs remain highly vulnerable to textual and visual jailbreaks, as well as prompt injections arXiv:2307.15043, Greshake et al., 2023, arXiv:2306.13213. Existing defenses often degrade performance through complex input transformations or treat...

Explainable Autonomous Cyber Defense Using Adversarial Multi-Agent Reinforcement Learning

Autonomous agents are increasingly deployed in both offensive and defensive cyber operations, creating high-speed, closed-loop interactions in critical infrastructure environments. Advanced Persistent Threat APT actors exploit "Living off the Land" techniques and targeted telemetry perturbations ...

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs against Evolving Multi-Round Attacks

As Large Language Models LLMs are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety concerns, especially those evolving over multi-round interactions. Existing defenses are largely reactive and struggle to adapt as adversaries refine...

Automating Cloud Security and Forensics through a Secure-By-Design Generative AI Framework

As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to meet emerging threats. Large Language Models LLMs have shown promise in automating log analysis and reasoning tasks, yet they remain vulnerable to prompt injection attacks and lack forensic...

Your Agent Is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt...

AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness against Large Language Models

Prompt injection has emerged as a critical vulnerability in large language model LLM deployments, yet existing research is heavily weighted toward defenses. The attack side -- specifically, which injection strategies are most effective and why -- remains insufficiently studied.We address this gap...

GHSA-RM5C-4RMF-VVHW OpenClaw: Sandbox file operations use check-then-act, bypassing fd-based TOCTOU defenses

Summary Sandbox file operations use check-then-act, bypassing fd-based TOCTOU defenses Current Maintainer Triage - Status: narrow - Normalized severity: medium - Assessment: Released workspace-only applypatch remove and mkdir operations were still check-then-act, but the draft overstates scope by...

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis

Agent Skills is an emerging open standard that defines a modular, filesystem-based packaging format enabling LLM-based agents to acquire domain-specific expertise on demand. Despite rapid adoption across multiple agentic platforms and the emergence of large community marketplaces, the security...

Cisco Secure Firewall Threat Defense Software IKEv2 DoS (cisco-sa-asa-ftd-ios-dos-kPEpQGGK)

According to its self-reported version, Cisco Firepower Threat Defense Software is affected by a vulnerability. - A vulnerability in the Internet Key Exchange version 2 IKEv2 feature of Cisco Secure Firewall Threat Defense FTD Software could allow an unauthenticated, remote attacker to trigger a...

Qilin EDR killer infection chain

Endpoint detection and response EDR tools are widely deployed and far more capable than traditional antivirus. As a result, attackers use EDR killers to disable or bypass them. Disabling telemetry collection process, memory, network activity limits what defenders can see and analyze. As defenders...

Synthetic Trust Attacks: Modeling How Generative AI Manipulates Human Decisions in Social Engineering Fraud

Imagine receiving a video call from your CFO, surrounded by colleagues, asking you to urgently authorise a confidential transfer. You comply. Every person on that call was fake, and you just lost $25 million. This is not a hypothetical. It happened in Hong Kong in January 2024, and it is becoming...

AEGIS: Adversarial Entropy-Guided Immune System -- Thermodynamic State Space Models for Zero-Day Network Evasion Detection

As TLS 1.3 encryption limits traditional Deep Packet Inspection DPI, the security community has pivoted to Euclidean Transformer-based classifiers e.g., ET-BERT for encrypted traffic analysis. However, these models remain vulnerable to byte-level adversarial morphing -- recent pre-padding attacks...

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that spans websites and sessions. While existing security research on memory assumes attackers can directly...

Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection across Attack Surfaces and Model Safety Tiers

We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate ASR; we localize the pipeline stage at which each model's defense activates. We instrument every run with a cryptographic canary token...

Safeguarding LLMs against Misuse and AI-Driven Malware Using Steganographic Canaries

AI-powered malware increasingly exploits cloud-hosted generative-AI services and large language models LLMs as analysis engines for reconnaissance and code generation. Simultaneously, enterprise uploads expose sensitive documents to third-party AI vendors. Both threats converge at the AI service...