Results for “Code”

Journal articles (OpenAlex) Barış Demirsatan · Religions Geopolitics

Translating Mahr into Secular Categories: Turkish Civil Law and the Legal Characterization of an Islamic Institution

The Turkish Civil Code of 1926, received from Switzerland, established a secular family law resting on numerus clausus and a broadly mandatory structure; yet mahr, an institution of Islamic family law, has persisted in social practice and, since the binding unification-of-case-law decision of the Court of Cassation of 2 December 1959, has been characterized as a donation contract governed by the law of obligations. This article analyzes that characterization doctrinally…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Ekaterina Romanova · Problems of Post-Communism Geopolitics

Discourse and Identity in East Germany: Divergent Narratives of the Russia-Ukraine Conflict

This article examines how anti-establishment parties contest Germany’s Zeitenwende. It codes 184 excerpts from Bundestag debates during the twentieth legislative term (2022−2024) and reads them alongside survey evidence on eastern German political culture. Drawing on discursive institutionalism, Feldman’s value-based identity theory, and ideational power, it finds that mainstream parties justify support for Ukraine through moral obligation, deterrence, and European…

Read at Journal articles (OpenAlex)

arXiv (research papers) Alex Remedios SI

Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents

To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before it runs (Auto Mode in Claude Code, Guardian in OpenAI's Codex). Prior evaluations of such monitors largely measure robustness to accidental harm or prompt injections from untrusted sources looking to hijack the agent. Less understood is how they hold up when the agent they monitor is persistently misaligned. To understand this…

Read at arXiv (research papers)

arXiv (research papers) Matteo Golinelli SI

AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination

AI agents for security inspect web pages, source code, logs, configuration files, and command outputs. These environments may contain deceptive artifacts that influence the agent's behavior. We call this adversarial task contamination. Whereas prompt injection relies on attacker-supplied instructions, task contamination also includes non-instructional evidence, such as fake results and decoy endpoints. We present AgentLSD, a controlled framework for studying adversarial task…

Read at arXiv (research papers)

arXiv (research papers) Viet K. Nguyen SI

An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks

Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also read images, which gives an attacker a way to put text into the agent's context without going through the user. We present MMPIBench, a reproducible benchmark that measures what happens next. It delivers a fixed set of attacks through six visual carriers (OCR text, overlays, EXIF metadata, QR codes, fake interfaces, and hybrids)…

Read at arXiv (research papers)

arXiv (research papers) Dimitrios Stamatios Bouras SI

Authority Is Not a String: A Capability-Scoped Harness for Prompt-Injection-Resistant Coding Agents

Coding agents use system-level tools to read files, execute commands, and modify source code. Within the agent's sandbox, these tools often carry ambient authority: naming a resource is sufficient to act on it. Indirect prompt injection exploits this authority by placing instructions in repository files or tool output that cause the agent to perform actions the user did not request. We propose CapScope, a harness-level authorization mechanism that restricts tool use without…

Read at arXiv (research papers)

arXiv (research papers) Shiqian Zhao SI

ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems

Recently, large language model (LLM) agents, such as Codex, Claude Code, and OpenClaw, have become capable of planning and executing long-horizon tasks through repeated tool calls. This capability also creates new opportunities for prompt injection. Existing attacks either place the malicious objective in one explicit instruction, making it easy to detect, or distribute the intent across multiple execution stages, making successful completion unreliable. In this work, we…

Read at arXiv (research papers)

Hacker News gr_norm SI

80% Prompt Injection Success Rate Against Claude Auto Mode

Article URL: https://embracethered.com/blog/posts/2026/breaking-claude-code-opus-5-and-automode/ Comments URL: https://news.ycombinator.com/item?id=49490671 Points: 3 # Comments: 1

Read at Hacker News

Simon Willison SI

Breaking Claude Code Opus 5 Auto Mode

Breaking Claude Code Opus 5 Auto Mode Anthropic are putting a great deal of faith in Claude Code's auto mode for protecting their coding agent users against prompt injection attacks. They recently made that the default and have made bold claims about its effectiveness. Johann Rehberger is one of the most credible prompt injection researchers active today. He found an attack against auto mode which he claims works 80% of the time, by tricking Claude Code into downloading and…

Read at Simon Willison

Inter-American Dialogue Ana Kourchenko Geopolitics

The Code and the Content

Mexico Program Fellow Gilberto García-Vazquez examines how the binding constraint on North American integration has shifted from tariffs to verification, and what that means for the Juárez–El Paso corridor.

Read at Inter-American Dialogue

arXiv (research papers) Jiahao Chen SI

Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds

Large Language Models (LLMs) have been integrated into complex ecosystems (e.g., Code Agents), while Indirect Prompt Injection (IPI) attacks have emerged as critical barriers to their safe deployment. Attackers exploit LLMs' indistinguishability between "instructions" and "data" to manipulate LLMs via maliciously injected instructions. Existing defenses, however, face an intractable safety-utility trade-off: most guardrails either incur high latency or suffer from severe…

Read at arXiv (research papers)

arXiv (research papers) Alexandre G. R. Day SI

Workspace Topology as an Attack Vector in Agentic Coding Assistants

Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This opens up a risk of malicious code being ingested as these coding tools operate with broad filesystem access inside developer workspaces. In this paper, we extensively study the impact of different dimensions of a novel attack surface we term workspace topology -- defined via directory depth, codebase modularity, in-file…

Read at arXiv (research papers)

arXiv (research papers) Md Jafrin Hossain SI

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community…

Read at arXiv (research papers)

South Asia @ LSE blog Sarkar,N Geopolitics

Fuel vs Education: Sri Lanka’s Digital Fix?

Sri Lanka has lived through several crises — civil war, natural disasters, bombings, a pandemic, economic collapse — to have learned something from them. Each emergency has left schools more fragile. Suren Ladd argues that the QR code that fixed fuel queues in the recent economic crises shows what a capable state can do when … Continued The post Fuel vs Education: Sri Lanka’s Digital Fix? first appeared on South Asia @ LSE.

Read at South Asia @ LSE blog

Simon Willison SI

Auto mode is now the default in Claude Code for Pro, Max, and Team plans

Auto mode is now the default in Claude Code for Pro, Max, and Team plans Anthropic are really confident in Claude Code's auto mode, to the point that they are making it the default setting for new sessions in most Claude Code plans starting on August 14th. This was one of the topics discussed in our Fireside Chat with Cat Wu and Thariq Shihipar at the AI Engineer World’s Fair last month. I asked them how they run Claude Code safely within Anthropic (given the threat of…

Read at Simon Willison

arXiv (research papers) Fred Zimmerman SI

Copyright Is the Headline; Capability Is the Blind Spot: AI Technology in the Book-Publishing Trade Press, November 2025--August 2026

This rapid evidence review examines 89 articles about artificial intelligence (AI) and book publishing published from November 1, 2025 through August 1, 2026. The purposive corpus spans English-, Chinese-, German-, French-, Spanish-, Portuguese-, Italian-, and Japanese-language publishing coverage; major-newspaper book coverage; and specialist technology commentators. Each item was coded for topic, stance, technical depth, and dominant voice. The press is neither silent nor…

Read at arXiv (research papers)

Journal articles (OpenAlex) Xuan Zhang, Yuan Tian, Jie Wang et al. · Electronics Space

Distance–Velocity Joint Extraction Method for Space Debris Based on Space-Based Single-Photon Ranging

Space-based single-photon ranging of space debris is affected by sparse signal photons, strong background noise, motion-induced echo broadening, and the amplification of local ranging errors during velocity estimation. To address these problems, this paper proposes a reliability-aware joint distance–velocity extraction framework that couples coded-echo processing with inter-window motion continuity. In each observation window, a phase-space trajectory matrix is constructed…

Read at Journal articles (OpenAlex)

Inquirer Global Nation ggaviola South China Sea

Asean, China target year-end SCS code of conduct; experts see hurdles

MANILA, Philippines – The Association of Southeast Asian Nations (Asean) and China are aiming to conclude negotiations on a long-awaited Code of Conduct (COC) in the South China Sea by the end of the year, marking the strongest push in years to finalize an agreement meant to help manage tensions in the disputed waterway. The

Read at Inquirer Global Nation

Inquirer Global Nation postie South China Sea

US reaffirms South China Sea stake as Asean-China talks advance

MANILA, Philippines — The United States on Friday reaffirmed its interests in the South China Sea as the Association of Southeast Asian Nations (Asean) and China move to accelerate negotiations on a long-awaited Code of Conduct (COC) for the disputed waterway. US Ambassador to Asean Kevin Kim said Washington respects the regional bloc’s negotiations with

Read at Inquirer Global Nation

arXiv (research papers) Akansha Shukla SI

Data Leakage Prevention in Agentic Applications via Preemptive Hardening

Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks. Enforcing required controls consistently is particularly challenging in workflows spanning many codebases and heterogeneous agents. To address this challenge in multi agentic systems, we present a pre-deployment pipeline for scanning, hardening, and validation of agentic…

Read at arXiv (research papers)

Journal articles (OpenAlex) Laurence Thieux, Alicia Olmo-Gómez · Mediterranean Politics Geopolitics

Legacy, memory and learning in the Algerian women’s movement: Strategic adaptation of the Hirak across overlapping arenas of authority

This article analyses how Algerian feminist organizations and collectives have confronted authoritarian power and entrenched patriarchal structures through learning processes. Despite their long history of mobilization, the role of Algerian feminists within broader oppositional movements remains understudied. By tracing three generations of feminist activism – from anti-colonial militants to reform-oriented advocates who challenged the 1984 Family Code and contemporary…

Read at Journal articles (OpenAlex)

Article 19 natashas

Tunisia: Blow for press freedom as journalist Haythem El Mekki sentenced

ARTICLE 19 condemns the conviction of journalist Haythem El Mekki under Article 86 of the Telecommunications Code for carrying out his journalistic work. This latest judgement reflects a broader pattern of judicial harassment and the criminalisation of journalists, media workers, activists, and other critics who report on or comment on matters of public interest. On

Read at Article 19

Embrace The Red Security

From Indirect Prompt Injection to DNS Exfiltration in macOS Terminal

This is a follow-up to my previous Terminal DiLLMa research, and there is a positive outcome: Apple fixed a macOS Terminal behavior that enabled a DNS-based data exfiltration technique. DNS Requests via ANSI Escape Codes David Leadbeater originally discovered an interesting behavior in the macOS Terminal app that allowed a special sequence of ANSI escape codes to issue DNS requests. In short, this triggered a DNS request from the macOS Terminal app:

Read at Embrace The Red

arXiv (research papers) Junhui Wang SI

PVDetector: Detecting Prompt Injection Attacks on Purpose-Specific LLM Agents through Policy-Violation Concept Analysis

Large language models (LLMs) are increasingly deployed as purpose-specific agents to handle domain-specific tasks such as customer service and code generation. These agents are expected to comply with not only generic safety guardrails but also purpose-specific restrictions tailored to their designated roles. Such additional restrictions enlarge the attack surface, particularly to prompt injection (PI) attacks. To defend against such attacks, existing detection methods…

Read at arXiv (research papers)

arXiv (research papers) SingGuard Team SI

SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification

We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion. We first introduce the NSFA taxonomy, which organizes 185 risk variants into a CIA-triad-grounded hierarchy and is cross-validated against three well-established OWASP guidelines. Based on this taxonomy, we construct a benchmark suite…

Read at arXiv (research papers)

arXiv (research papers) Zhongzheng Xu SI

"Code Is Cheap. Show Me the Talk.": Lessons from Teaching and Managing AI Coding Tool Usage in a Visualization Course

Generative Artificial Intelligence (GenAI) coding tools are transforming visualization education. They can assist with implementation and design, but they can also let students bypass intended learning trajectories. In this paper, we share our retrospective experience managing and teaching AI use in an upper-level visualization course. We implemented prompt injections, asked oral checkout questions, and taught two AI coding labs. Prior to our coding labs, at least half of…

Read at arXiv (research papers)

Monthly Review (Marxist) Monthly Review Press Geopolitics

Andy Merrifield’s many books, from “Roses for Gramsci” to “Marx, Dead and Alive”

The latest: "....Is 'subaltern' a code for the working classes? Is 'hegemony' an economic force or a cultural power? Are 'organic intellectuals' inherently more progressive? The answers to such questions depend upon your choice of scholar—whether, say, you’re reading a Foucauldian literary critic or a Marxist sociologist, a subaltern historian or a posthuman anthropologist. Over the years, Gramsci’s writing has been polished by critics of such diverse persuasions that it has…

Read at Monthly Review (Marxist)

arXiv (research papers) Josh Hills SI

Distributed Attacks in Persistent-State AI Control

As AI coding agents become more autonomous, they increasingly ship code iteratively, with the codebase persisting across sessions. This persistence creates a new attack surface: a misaligned or prompt-injected agent can distribute attacks across pull requests (PRs) and time its payload for the PR with the best natural cover. To study the resulting dynamics, we introduce Iterative VibeCoding, a setting for AI control, the study of safely deploying capable but potentially…

Read at arXiv (research papers)

The Guardian Mali Sarah Johnson

‘Witch-hunt’ in Niger as military regime rounds up LGBTQ+ population

Fears of resurgence of HIV/Aids amid loss of access to PrEP drugs as at least 40 people arrested in ‘toxic’ climate A “witch-hunt” is under way in Niger, where dozens of people have been arrested for homosexuality in the west African state following the introduction of a new penal code earlier this year. Up to 40 people have been arrested and 16 men, including high-ranking military officials, have been imprisoned across the country, according to local media.

Read at The Guardian Mali

Journal articles (OpenAlex) Nihat Ali Özcan, Erol Başaran BURAL · Dynamics of Asymmetric Conflict Geopolitics

Self-criticism mechanism in Marxist–Leninist oriented organizations: the PKK case

In Marxist/Leninist oriented organizations, self-criticism mechanism is intended to rectify performance errors and correct the path towards realizing the organizational mission as it is embodied in its goals and objectives. This article focuses on the self-criticism culture within the militant ranks of the Marxist/Leninist-oriented PKK insurgent group. It explores the contexts of the self-criticism, by using empirically coded thematic analysis of primary sources…

Read at Journal articles (OpenAlex)

Older stories