magescan

Mage Scan The idea behind this is to evaluate the quality and security of a Magento site you don't have access to. The scenario when you're interviewing a potential developer or vetting a new client and want to have an idea of what you're getting into. Installation .phar Download the magescan.pha...

ORBIT: A Framework for Multi-Agent Safety and Security Evaluations

Multi-agent LLM systems are increasingly deployed for complex, long-horizon tasks or emerge as a natural consequence of agents interacting in the wild. Yet they give rise to significant safety and security risks: the flexible protocols that enable task generalization also expose novel threats, fr...

ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-Based Agents

Large language model LLM agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. However, existing studies largely rely on manually implemented or reused environments, stochastic LLM-based tool simulation, and predefined injection...

Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

Autonomous multi-agent systems AMAS built on large language models LLMs, such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively...

⚡ Weekly Recap: Rogue AI Agents, Check Point Exploit, Slopsquatting, ClickFix Lures and More

Monday starts with the usual promise that everything is under control. Then the logs wake up. This week, trusted tools crossed lines, old flaws found new work, exposed systems stayed exposed, and attackers kept hiding inside normal-looking services. Nothing looked strange at first. That helped...

How Do You Choose Your AI Component? an Interview Study of Secure AI Integration in Practice

The increasing adoption of Large Language Models LLMs as AI components in modern software systems introduces distinct security risks to the software supply chain. While many considerations and safety mechanisms are in place for components of the traditional software supply chain, the recent rapid...

SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents

Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabilities enable complex real-world workflows, they also introduce security risks that are difficult to capture with existing evaluations. Current agent...

BYOT-CPS: A Hybrid Cyber-Physical Systems Testbed for IoT Security Assessment and Platform Evaluation

Internet of Things IoT security research continues to face a methodological gap between scalable virtual experimentation and realistic device behaviour. While pure simulation and emulation platforms provide control, repeatability, and scale, they do not fully reproduce firmware-specific behaviour...

Practical Countermeasure against Attacks Exploiting Detection Efficiency Mismatch in Quantum Key Distribution

We demonstrate a practical countermeasure against a well-known class of attacks on quantum key distribution QKD systems that exploit detection efficiency mismatch, where the receiver's detectors do not exhibit identical responses to incoming photons across all degrees of freedom. This class of...

Exploit for Deserialization of Untrusted Data in Facebook React

CVE-2025-55182 Security Lab "React2Shell" This repository c...

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications

Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or refusal-policy intervention. Ablating Safety studies...

OpenAI’s GPT-5.5 is as Good as Mythos at Finding Security Vulnerabilities

The UK's AI Security Institute evaluated GPT-5.5's ability to find security vulnerabilities, and found that it is comparable to Claude Mythos. Note that the OpenAI model is generally available. Here is the Institute's evaluation of Mythos. And here is an analysis of a smaller, cheaper model. It...

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in...

GoAT-X: A Graph of Auditing Thoughts for Securing Token Transactions in Cross-Chain Contracts

Cross-chain bridges, the critical infrastructure of the multi-chain ecosystem, have become a primary target for attackers, resulting in over $2.8 billion in losses due to subtle implementation flaws. Existing defenses, such as bytecode-level static analysis, are ill-equipped to handle the semanti...

AVISE: Framework for Evaluating the Security of AI Systems

As artificial intelligence AI systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-profile exploits and consequential system failures. Yet systematic approaches to evaluating AI security remain underdeveloped. In this paper, we...

CVE-2026-33622 A PinchTab Security Policy Bypass in /wait Allows Arbitrary JavaScript Execution

PinchTab is a standalone HTTP server that gives AI agents direct control over a Chrome browser. PinchTab v0.8.3 through v0.8.5 allow arbitrary JavaScript execution through POST /wait and POST /tabs/id/wait when the request uses fn mode, even if security.allowEvaluate is disabled. POST /evaluate...

Quantifying Memory Cells Vulnerability for DRAM Security

Dynamic Random Access Memory DRAM is pervasive in computer systems. Cell vulnerabilities caused by unintended phenomena forced retention failure, latency alteration, rowhammer and rowpress lead to unintended bit flips in memory. These phenomena have been explored as attacks to violate data...

TOSSS: A CVE-Based Software Security Benchmark for Large Language Models

With their increasing capabilities, Large Language Models LLMs are now used across many industries. They have become useful tools for software engineers and support a wide range of development tasks. As LLMs are increasingly used in software development workflows, a critical question arises: are...

Security Considerations for Multi-Agent Systems

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct security vulnerabilities from those documented for singular AI...

EVMbench: Evaluating AI Agents on Smart Contract Security

Smart contracts on public blockchains now manage large amounts of value, and vulnerabilities in these systems can lead to substantial losses. As AI agents become more capable at reading, writing, and running code, it is natural to ask how well they can already navigate this landscape, both in way...