Related papers: Malicious Or Not: Adding Repository Context to Age…
New contributors often struggle to find tasks that they can tackle when onboarding onto a new Open Source Software (OSS) project. One reason for this difficulty is that issue trackers lack explanations about the knowledge or skills needed…
Open-source AI libraries are foundational to modern AI systems, yet they present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity, and regulatory compliance. We introduce LibVulnWatch, a…
Users often interpret and select agent skills through their SKILL markdown specifications. To protect users, existing audits mainly focus on malicious or unsafe skills. We study the complementary question of whether specifications help…
Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…
Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doing so confers a strategic advantage. To investigate this phenomenon, we…
Agentic AI systems are increasingly capable of performing professional and personal tasks with limited human involvement. However, tracking these developments is difficult because the AI agent ecosystem is complex, rapidly evolving, and…
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic…
The NPM ecosystem has become a primary target for software supply chain attacks, yet existing detection tools are evaluated in isolation on incompatible datasets, making cross-tool comparison unreliable. We conduct a benchmark-driven…
Large language models (LLMs) are increasingly deployed as tool-using agents, shifting safety concerns from harmful text generation to harmful task completion. Deployed systems often condition on user profiles or persistent memory, yet agent…
Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question…
Generative AI is transforming the provision of expert services. This article uses a series of one-shot experiments to quantify the behavioral, welfare and distribution consequences of large language models (LLMs) on AI-AI, Human-Human,…
Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, such as malicious Web content, files, email attachments, and…
Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable…
Agent skills - structured packages of instructions, scripts, and references that augment a large language model (LLM) without modifying the model itself - have moved from convenience to first-class deployment artifact. The runtime that…
Website hacking is a frequent attack type used by malicious actors to obtain confidential information, modify the integrity of web pages or make websites unavailable. The tools used by attackers are becoming more and more automated and…
Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents learning to…
The democratization of generative AI introduces new forms of human-AI interaction and raises urgent safety, ethical, and cybersecurity concerns. We develop a socio-technical explanation for how generative AI enables and scales cybercrime.…
As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase the abilities of such agents to act against human well being in service of corporate authority. Building on Agentic…
The temporal nature of modeling accounts as nodes and transactions as directed edges in a directed graph -- for a blockchain, enables us to understand the behavior (malicious or benign) of the accounts. Predictive classification of accounts…
The open-source software (OSS) ecosystem suffers from security threats caused by malware.However, OSS malware research has three limitations: a lack of high-quality datasets, a lack of malware diversity, and a lack of attack campaign…