Results for “Code”

arXiv (research papers) Ninghui Li SI

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic systems used by millions of users and thousands of enterprises in both controlled and open-world environments. Agent architectures change core assumptions around code-data separation…

Read at arXiv (research papers)

Simon Willison SI

Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager

Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager Adnan Khan describes a devious attack chain against the Cline GitHub repository, which started with a prompt injection attack in the title of an issue opened against the repo. Cline were running AI-powered issue triage using the anthropics/claude-code-action@v1 action, configured to run Claude Code with --allowedTools "Bash,Read,Write,..." any time any user opened an issue in their…

Read at Simon Willison

Google Project Zero Ivan Fratric Security

On the Effectiveness of Mutational Grammar Fuzzing

Mutational grammar fuzzing is a fuzzing technique in which the fuzzer uses a predefined grammar that describes the structure of the samples. When a sample gets mutated, the mutations happen in such a way that any resulting samples still adhere to the grammar rules, thus the structure of the samples gets maintained by the mutation process. In case of coverage-guided grammar fuzzing, if the resulting sample (after the mutation) triggers previously unseen code coverage, this…

Read at Google Project Zero

Journal articles (OpenAlex) Federica Spadazzi, Dalila Tripi, Miriam Ottaviani et al. · Forensic Sciences Geopolitics

Gender-Based Violence and Femicide: A Comparative Analysis of the Evolution of International and Italian Legislation to Identify Appropriate Clinical and Judicial Management of Victims of Abuse—The “Pink Code” Pathway and Its Medico-Legal Implications

Introduction: Gender-based violence and femicide represent the most extreme manifestation of a deep-rooted cultural distortion embedded within patriarchal social structures. In this study, adopting a comparative and multidisciplinary approach, we analyzed the evolution of international legislation and the major historical milestones in the protection of women’s rights and the prevention of gender-based violence at both the global and Italian levels. Specific protocols such…

Read at Journal articles (OpenAlex)

arXiv (research papers) Junjie Chu SI

Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks

The rapid expansion of research in LLM safety presents challenges in tracking advancements, making benchmarks important evaluation infrastructures for identifying key trends and facilitating systematic comparisons. Yet no systematic assessment exists of their code quality and runnability, nor of what factors are associated with the community's adoption of certain benchmarks over others. To address this gap, we conduct a systematic measurement study of 31 LLM safety…

Read at arXiv (research papers)

arXiv (research papers) Martin Odersky SI

Tracking Capabilities for Safer Agents

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these challenges, we propose to put the agent in a programming-language-based "safety harness": instead of calling tools directly, agents express their intentions as code in a capability-safe language: Scala 3 with capture checking. Capabilities are…

Read at arXiv (research papers)

arXiv (research papers) David Schmotz SI

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates an increasingly complex agent supply chain, offering new surfaces for prompt injection attacks. We identify skill-based prompt injection as a significant threat and introduce…

Read at arXiv (research papers)

arXiv (research papers) Lei Ba SI

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context. To bridge this gap, we introduce CIBER, an automated benchmark that combines dynamic attack…

Read at arXiv (research papers)

arXiv (research papers) Kiarash Ahi SI

Trustworthy AI LLM Scalability Risk Index (LSRI): A Cybersecurity Framework Assessing Agentic-AI Security & Software Model Supply Chain Safety Boosting AI-Generated Malware Defense & Explainability Mitigating Emerging Risks of Generative AI

As AI shifts from human-in-the-loop interfaces to autonomous multi-agent systems capable of real-time code execution and tool integration through protocols like the Model Context Protocol (MCP), traditional SAST, DAST, and legacy AI safety methods fail to detect modern agentic-AI threats. This paper introduces the LLM Scalability Risk Index (LSRI), a parametric framework and cybersecurity standard for stress-testing autonomous orchestration pipelines. LSRI measures the…

Read at arXiv (research papers)

Inquirer Global Nation dlejano South China Sea

China-PH ‘word war’ may delay South China Sea code – Tulfo

MANILA, Philippines – Senate Committee on Foreign Relations chairman Sen. Erwin Tulfo on Wednesday said the escalation of exchanges between the Chinese Embassy and Philippine officials may delay the approval of the South China Sea Code of Conduct. Following a meeting with Department of Foreign Affairs (DFA) Secretary Theresa Lazaro, Tulfo said the agency had

Read at Inquirer Global Nation

Rappler Rappler.com South China Sea

What you should know about ASEAN-China talks on Code of Conduct in South China Sea

The proposed COC is meant to set rules to prevent incidents and reduce tensions in the South China Sea, where several ASEAN member states and China assert overlapping claims

Read at Rappler

arXiv (research papers) Narek Maloyan SI

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems

The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language Models (LLMs) integrated with external tools, file systems, and shell access through protocols like the Model Context Protocol (MCP). However, this expanded capability surface introduces critical security vulnerabilities. In this…

Read at arXiv (research papers)

arXiv (research papers) Yi Liu SI

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a significant yet uncharacterized attack surface. We conduct the first large-scale empirical security analysis of this emerging ecosystem, collecting 42,447 skills from two major marketplaces…

Read at arXiv (research papers)

Simon Willison SI

First impressions of Claude Cowork, Anthropic's general agent

New from Anthropic today is Claude Cowork, a "research preview" that they describe as "Claude Code for the rest of your work". It's currently available only to Max subscribers ($100 or $200 per month plans) as part of the updated Claude Desktop macOS application. Update 16th January 2026: it's now also available to $20/month Claude Pro subscribers. I've been saying for a while now that Claude Code is a "general agent" disguised as a developer tool. It can help you with any…

Read at Simon Willison

arXiv (research papers) Guanquan Shi SI

SoK: Trust-Authorization Mismatch in LLM Agent Interactions

Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts control from deterministic code to probabilistic inference, creating a fundamental Trust-Authorization Mismatch: static permissions are structurally decoupled from the agent's fluctuating runtime trustworthiness. In this Systematization of Knowledge (SoK), we survey more than 200 representative papers to…

Read at arXiv (research papers)

Journal articles (OpenAlex) Mohammad Amaan Siddiqui · Nations and Nationalism Geopolitics

Rhetorics of Counternationalism: The Limitations of Digital Anti‐Hindutva in Combating Right‐Wing Extremism

ABSTRACT How are online discourses in subissues within counternationalist movements constructed? This study better understands what comprises digital counternationalist dissent against right‐wing nationalism, finding that right‐wing nationalism's success can also be explained through limitations in counternationalist discourse. In this project, three coders analysed dissent against India's right‐wing nationalism, Hindutva, parsing anti‐Hindutva into different themes for…

Read at Journal articles (OpenAlex)

Simon Willison SI

Google Antigravity Exfiltrates Data

Google Antigravity Exfiltrates Data PromptArmor demonstrate a concerning prompt injection chain in Google's new Antigravity IDE: In this attack chain, we illustrate that a poisoned web source (an integration guide) can manipulate Gemini into (a) collecting sensitive credentials and code from the user’s workspace, and (b) exfiltrating that data by using a browser subagent to browse to a malicious site. The attack itself is hidden in 1px font on a web page claiming to offer an…

Read at Simon Willison

Simon Willison SI

Claude Opus 4.5, and why evaluating new LLMs is increasingly difficult

Anthropic released Claude Opus 4.5 this morning, which they call "best model in the world for coding, agents, and computer use". This is their attempt to retake the crown for best coding model after significant challenges from OpenAI's GPT-5.1-Codex-Max and Google's Gemini 3, both released within the past week! The core characteristics of Opus 4.5 are a 200,000 token context (same as Sonnet), 64,000 token output limit (also the same as Sonnet), and a March 2025 "reliable…

Read at Simon Willison