Agents of Chaos

We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week period, twenty AI researchers interacted with the agents unde...

Who Approved This Agent? Rethinking Access, Accountability, and Risk in the Age of AI Agents

AI agents are accelerating how work gets done. They schedule meetings, access data, trigger workflows, write code, and take action in real time, pushing productivity beyond human speed across the enterprise. Then comes the moment every security team eventually hits: “Wait… who approved this?”...

Securing Agentic AI Systems -- a Multilayer Security Framework

Securing Agentic Artificial Intelligence AI systems requires addressing the complex cyber risks introduced by autonomous, decision-making, and adaptive behaviors. Agentic AI systems are increasingly deployed across industries, organizations, and critical sectors such as cybersecurity, finance, an...

Building Trustworthy AI Agents

The promise of personal AI assistants rests on a dangerous assumption: that we can trust systems we haven’t made trustworthy. We can’t. And today’s versions are failing us in predictable ways: pushing us to do things against our own best interests, gaslighting us with doubt about things we are or...

AAGATE: A NIST AI RMF-Aligned Governance Platform for Agentic AI

This paper introduces the Agentic AI Governance Assurance & Trust Engine AAGATE, a Kubernetes-native control plane designed to address the unique security and governance challenges posed by autonomous, language-model-driven agents in production. Recognizing the limitations of traditional...

Why Software Signing (Still) Matters: Trust Boundaries in the Software Supply Chain

Software signing provides a formal mechanism for provenance by ensuring artifact integrity and verifying producer identity. It also imposes tooling and operational costs to implement in practice. In an era of centralized registries such as PyPI, npm, Maven Central, and Hugging Face, it is...

EUVD-2025-5966

Malicious code in bioql PyPI...

Security and Privacy Analysis of Tile's Location Tracking Protocol

We conduct the first comprehensive security analysis of Tile, the second most popular crowd-sourced location-tracking service behind Apple's AirTags. We identify several exploitable vulnerabilities and design flaws, disproving many of the platform's claimed security and privacy guarantees: Tile's...

The Signalgate Case Is Waiving a Red Flag to All Organizational and Behavioral Cybersecurity Leaders, Practitioners, and Researchers: Are We Receiving the Signal Amidst the Noise?

The Signalgate incident of March 2025, wherein senior US national security officials inadvertently disclosed sensitive military operational details via the encrypted messaging platform Signal, highlights critical vulnerabilities in organizational security arising from human error, governance gaps...

Never Compromise to Vulnerabilities: a Comprehensive Survey on AI Governance

The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including misinformation, inequity, security breaches, physical harm, and eroded...

Policy Design in Zero-Trust Distributed Networks: Challenges and Solutions

Traditional security architectures are becoming more vulnerable to distributed attacks due to significant dependence on trust. This will further escalate when implementing agentic AI within the systems, as more components must be secured over a similar distributed space. These scenarios can be...

From Permissioned to Proof-of-Stake Consensus

This paper presents the first generic compiler that transforms any permissioned consensus protocol into a proof-of-stake permissionless consensus protocol. For each of the following properties, if the initial permissioned protocol satisfies that property in the partially synchronous setting, the...

Data Breach Reporting for regulatory requirements with Microsoft Data Security Investigations​​

Seventy-four percent of organizations surveyed experienced at least one data security incident with their business data exposed in the previous year as reported in Microsoft’s Data Security Index: Trends, insights, and strategies to secure data report. Despite the best people, process and...

Centralized Trust in Decentralized Systems: Unveiling Hidden Contradictions in Blockchain and Cryptocurrency

Blockchain technology promises to democratize finance and promote social equity through decentralization, but questions remain about whether current implementations advance or hinder these goals. Through a mixed-methods study combining semi-structured interviews with 13 diverse blockchain...

Security-First AI: Foundations for Robust and Trustworthy Systems

The conversation around artificial intelligence AI often focuses on safety, transparency, accountability, alignment, and responsibility. However, AI security i.e., the safeguarding of data, models, and pipelines from adversarial manipulation underpins all of these efforts. This manuscript posits...

Naming Is Framing: How Cybersecurity'S Language Problems Are Repeating in AI Governance

Language is not neutral; it frames understanding, structures power, and shapes governance. This paper argues that misnomers like cybersecurity and artificial intelligence AI are more than semantic quirks; they carry significant governance risks by obscuring human agency, inflating expectations, a...

Directus's webhook trigger flows can leak sensitive data

Describe the Bug In Directus, when a Flow with the "Webhook" trigger and the "Data of Last Operation" response body encounters a ValidationError thrown by a failed condition operation, the API response includes sensitive data. This includes environmental variables, sensitive API keys, user...

GHSA-FM3H-P9WM-H74H Directus's webhook trigger flows can leak sensitive data

Describe the Bug In Directus, when a Flow with the "Webhook" trigger and the "Data of Last Operation" response body encounters a ValidationError thrown by a failed condition operation, the API response includes sensitive data. This includes environmental variables, sensitive API keys, user...

CVE-2025-30353 Directus's webhook trigger flows can leak sensitive data

Directus is a real-time API and App dashboard for managing SQL database content. Starting in version 9.12.0 and prior to version 11.5.0, when a Flow with the "Webhook" trigger and the "Data of Last Operation" response body encounters a ValidationError thrown by a failed condition operation, the A...

CVE-2025-22271 IP Spoofing in CyberArk Endpoint Privilege Manager

The application or its infrastructure allows for IP address spoofing by providing its own value in the "X-Forwarded-For" header. Thus, the action logging mechanism in the application loses accountability This issue affects CyberArk Endpoint Privilege Manager in SaaS version 24.7.1. The status of...