Will Chinese megaprojects solve northern Peru’s water crisis?
China has won an international tender to execute the Poechos and Alto Piura megaprojects, both key to the Piura region’s future water security
China has won an international tender to execute the Poechos and Alto Piura megaprojects, both key to the Piura region’s future water security
Military intelligence chief reportedly also killed in sweeping attacks by jihadists and separatist rebels Mali’s militant attacks expose limits of Putin’s power in Africa Mali has been left reeling from sweeping attacks by jihadists and separatist rebels who seized several towns and military bases and killed the defence minister and military intelligence chief. The weekend assault on the west African state’s security architecture was coordinated by al-Qaida-affiliated…
Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt injection. Existing defenses face significant challenges in balancing security with utility, often encountering a trade-off where rigorous protection leads to over-defense, or where subtle indirect injections bypass detection. Drawing inspiration…
Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat judgement entirely untrained. We present ClawdGo, a framework for endogenous security awareness training: we teach the agent to recognise and reason about threats from the inside, at inference time, with no model modification. Four…
Abstract Grounded in realism, geopolitical techno-nationalism advocates restricting technology outflows to targeted entities from rival countries to safeguard national security and technological superiority. We examine this logic in international standard-setting organizations (ISSOs), which exemplify decentralized innovation ecosystems that shape future-generation technologies. We identify a paradox: techno-nationalist restrictions would unintentionally undermine, rather…
Autonomous Large Language Model (LLM) agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorized tool execution. Securing these systems requires effective information flow tracking. Yet, traditional taint analysis that is designed for program memory states fundamentally…
Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge not only at the prompt interface but also through architectural state, delegated authority, and long-horizon interactions. Existing security taxonomies, however, primarily organize threats by attack type, such as prompt injection or…
AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., personal and financial information). This poses a serious risk to security and privacy: an AI model may hallucinate or make mistakes, and adversaries may attack it (e.g., via prompt injection) to exfiltrate user data. This paper presents GAAP (Guaranteed Accounting for Agent Privacy), an execution environment for AI agents that…
Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic lights are essential in-band signals that can and should influence agent behavior. However, similar signals could also be crafted to operate as misleading visual injections, overriding user intent and posing security risks. This duality…
This article investigates the perspectives of people working at the intersection of Green politics and the military in Germany, a country currently redefining its approach to security policy as a result of the Russian invasion of Ukraine. It takes as a starting point the tension between the conventional security paradigm, i.e. the idea that security is something militaries provide for the nation-state, and the need to mitigate the environmental and climate crisis given the…
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection. This paper presents SafeAgent, a runtime security architecture that treats agent safety as a stateful decision problem over evolving interaction trajectories. The proposed design separates execution governance from semantic risk reasoning…
This paper critically re-examines prevailing interpretations of Iran’s regional policy in sponsoring the axis of resistance, with particular focus on the theory of forward defence. The uncoordinated Hamas attack on Israel on October 7, which put Iran in grave danger, challenged the assumption that Tehran has established resistance groups for defensive purposes. Despite the security costs of Hamas’s unilateral action, Iran maintained support for the group, suggesting that its…
Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on vulnerabilities within skills, such as prompt injection. However, there is a critical gap regarding skills that may be misused for harmful actions (e.g., cyber attacks, fraud and scams, privacy violations, and sexual content generation)…
Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous, high-dimensional audio channel. While prior work studied audio jailbreaks, the security risks of malicious audio injection and downstream behavior manipulation remain underexamined. In this work, we reveal a previously overlooked threat…
This paper analyses the anti-partisan war waged by the rebel forces during the Spanish Civil War and later by Franco’s dictatorship between 1936 and 1952. It argues that Spain constituted the earliest and longest-lasting case of anti-fascist armed resistance in twentieth-century Europe and, correspondingly, one of the first sites of modern counterinsurgency conducted by a fascist regime. Drawing on military orders, judicial records and internal security documentation, the…
FinBot is a hands-on companion to the OWASP GenAI Security Project, offering an interactive Capture-The-Flag environment built around a simulated financial services application. Designed as the 'Juice Shop for the Agentic AI', it lets builders and defenders explore agentic risks in a live, multi-agent system with real tool access.
OWASP GenAI Exploit Round-up Report Q1 2026 Coverage period: January 1, 2026 through April 11, 2026 Overview For the last two years the OWASP GenAI Security Project published a list of the major incidents for the last quarter. This is not designed to be an exhaustive report. This report consolidates major AI-related security incidents and
Prompt injection has emerged as a critical security threat to large language models (LLMs), yet existing studies predominantly focus on single-dimensional attack strategies, such as semantic rewriting or character-level obfuscation, which fail to capture the combined effects of multi-space perturbations in realistic scenarios. In addition, systematic black-box robustness evaluations of recent Chinese LLMs, such as DeepSeek, remain limited. To address these gaps, we propose…
Philippine security officials claim to have discovered plastic bottles of cyanide on Chinese boats close to Second Thomas Shoal in the Spratly Islands.
Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs bypass safety mechanisms to elicit harmful outputs, poses significant security risks. While prior work has primarily focused on prompt injection attacks, these approaches often require resource-intensive prompt engineering and overlook other critical components, such as chat templates. This paper introduces TEMPLATEFUZZ, a…
The applications of Generative Artificial Intelligence (GenAI) and their intersections with data-driven fields, such as healthcare, finance, transportation, and information security, have led to significant improvements in service efficiency and low latency. However, this synergy raises serious concerns regarding the security of large language models (LLMs) and their potential impact on the privacy of companies and users' data. Many technology companies that incorporate LLMs…
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by embedding malicious instructions within tool-returned content, which agents directly incorporate into their conversation history as trusted observations. To address these vulnerabilities, we introduce \textsc{ClawGuard}, a novel runtime security…
The National Security Council announces the findings of an investigation
Bookmark this page to catch the livestream at around 10 am on April 13
Using Plan Colombia as a model, the United States should commit to a long-term, well-funded effort to bring security to Venezuela.
On November 19, 2025, Mark Shepherd, Lieutenant-Commander in the Canadian Armed Forces (CAF), presented CAF Information Operations Evolution: From Afghanistan to Modern High-Readiness Capability at the 2025 West Coast Security Conference. The presentation was followed by a question-and-answer period with audience members and CASIS Vancouver executives. The presentation examined the evolution of CAF Information Operations (IO), doctrinal development from Afghanistan to…
Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the community faces a critical gap: the lack of a unified platform for prompt injection evaluation. This makes it challenging to reliably compare defenses, understand their true robustness under diverse attacks, or assess how well they generalize across tasks and benchmarks. For instance, many defenses initially reported as effective were…
Generative Artificial Intelligence (GenAI) has become a central component of many development tools (e.g., GitHub Copilot) that support software practitioners across multiple programming tasks, including code completion, documentation, and bug detection. However, current research has identified significant limitations and open issues in GenAI, including reliability, non-determinism, bias, and copyright infringement. While prior work has primarily focused on assessing the…