English
Related papers

Related papers: Malicious Or Not: Adding Repository Context to Age…

200 papers

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Artificial Intelligence · Computer Science 2026-05-26 Jinhu Qi , Muzhi Li , Jiahong Liu , Yuqin Shu , Dianzhi Yu , Shicheng Ma , Wenqian Cui , Yiyang Zhao , Yiyi Chen , Ruoxi Jiang , Irwin King , Zenglin Xu

Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. We observe that this often produces a "confused -> re-retrieve ->…

Programming Languages · Computer Science 2026-05-28 Xinze Li , Yuhang Zang , Yixin Cao , Aixin Sun

Programmatic skills in LLM ecosystems consist of a natural-language description and executable implementation files. Users and LLMs rely on the description to understand the skill's scope. However, the implementation may perform…

Cryptography and Security · Computer Science 2026-05-14 Wenhui He , Yue Li , Bang Fu , Huan Xing , Xing Fan , ZeHua Zhang , Baoning Niu

We study whether adoption of an AI coding assistant causally expands the technological frontier of individual software developers. We exploit the staggered rollout of Claude Code across GitHub between May 2025 and January 2026 in a panel of…

General Economics · Economics 2026-05-26 Alexander Quispe

Agent skills are increasingly used to extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources. While improving reusability, this modular design also introduces a new supply-chain attack surface: a…

Cryptography and Security · Computer Science 2026-05-19 Xiaojun Jia , Jie Liao , Simeng Qin , Jindong Gu , Wenqi Ren , Xiaochun Cao , Yang Liu , Philip Torr

The gossip-based distributed algorithms are widely used to solve decentralized optimization problems in various multi-agent applications, while they are generally vulnerable to data injection attacks by internal malicious agents as each…

Machine Learning · Computer Science 2021-01-19 Sissi Xiaoxiao Wu , Gangqiang Li , Shengli Zhang , Xiaohui Lin

Agentic AI systems can plan, call tools, inspect code, interact with web applications, and coordinate multi-step workflows. These same capabilities change the economics of cyber offense. The central near-term risk is not that every…

Cryptography and Security · Computer Science 2026-05-11 Christopher Koch

Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…

Machine Learning · Computer Science 2026-01-22 Amine Andam , Jamal Bentahar , Mustapha Hedabou

Artificial Intelligence systems, which benefit from the availability of large-scale datasets and increasing computational power, have become effective solutions to various critical tasks, such as natural language understanding, speech…

Software Engineering · Computer Science 2023-03-20 Zhou Yang , Chenyu Wang , Jieke Shi , Thong Hoang , Pavneet Kochhar , Qinghua Lu , Zhenchang Xing , David Lo

We investigate whether giving LLM agents the collaborative tools and autonomy that humans naturally use for problem solving can improve their performance. We equip Claude Code agents with MCP-based social media and journaling tools and…

Artificial Intelligence · Computer Science 2025-09-18 Harper Reed , Michael Sugimura , Angelo Zangari

When AI agents operating with access to sensitive information encounter a conflict between completing an assigned task and following rules or ethical constraints, they can resort to unsanctioned behaviour. Existing inference time safety…

Cryptography and Security · Computer Science 2026-05-01 Francesca Gomez

Smart contracts are self-executing programs that manage financial transactions on blockchain networks. Developers commonly rely on third-party code libraries to improve both efficiency and security. However, improper use of these libraries…

Software Engineering · Computer Science 2026-04-02 Yishun Wang , Wenkai Li , Xiaoqi Li , Zongwei Li , Lei Xie , Yuqing Zhang

Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with complex attacks, while human auditors are thorough but slow…

Cryptography and Security · Computer Science 2026-01-13 Arthur Gervais , Liyi Zhou

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are…

Artificial Intelligence · Computer Science 2026-04-10 Ziyu Ma , Shidong Yang , Yuxiang Ji , Xucong Wang , Yong Wang , Yiming Hu , Tongwen Huang , Xiangxiang Chu

Personalized computer-use agents are rapidly moving from expert communities into mainstream use. Unlike conventional chatbots, these systems can install skills, invoke tools, access private resources, and modify local environments on users'…

Cryptography and Security · Computer Science 2026-04-01 Zifan Peng , Mingchen Li

Software development relies on code reuse to minimize costs, creating vulnerability risks through dependencies with substantial economic impact, as seen in the Crowdstrike and HeartBleed incidents. We analyze 52,897 dependencies across…

Econometrics · Economics 2025-07-02 Cornelius Fritz , Co-Pierre Georg , Angelo Mele , Michael Schweinberger

Coding agents have received significant adoption in software development recently. Unlike traditional LLM-based code completion tools, coding agents work with autonomy (e.g., invoking external tools) and leave visible traces in software…

Software Engineering · Computer Science 2026-02-03 Andre Hora , Romain Robbes

Existing malicious code detection techniques demand the integration of multiple tools to detect different malware patterns, often suffering from high misclassification rates. Therefore, malicious code detection techniques could be enhanced…

Cryptography and Security · Computer Science 2025-01-07 Nusrat Zahan , Philipp Burckhardt , Mikola Lysenko , Feross Aboukhadijeh , Laurie Williams

LLM agents increasingly rely on reusable skills (e.g., `SKILL.md`) to execute complex tasks, yet these artifacts lack portability: agent frameworks are highly sensitive to prompt formatting, leading to a large performance variation for the…

Cryptography and Security · Computer Science 2026-05-12 Yipeng Ouyang , Yi Xiao , Yuhao Gu , Xianwei Zhang

In detecting malicious websites, a common approach is the use of blacklists which are not exhaustive in themselves and are unable to generalize to new malicious sites. Detecting newly encountered malicious websites automatically will help…

Cryptography and Security · Computer Science 2022-09-21 Adebayo Oshingbesan , Courage Ekoh , Chukwuemeka Okobi , Aime Munezero , Kagame Richard