Related papers: Malicious Or Not: Adding Repository Context to Age…
The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propose AgentSkillOS, the first principled framework for skill…
Random rules improve a coding agent's task performance as much as expert-curated ones (both $+13.8$pp on a discriminative subset of SWE-bench Verified), and in our data every individually beneficial rule is a negative constraint ("do not…
The Amazon Alexa marketplace is the largest Voice Personal Assistant (VPA) platform with over 100,000 voice applications (i.e., skills) published to the skills store. In an effort to maintain the quality and trustworthiness of voice-apps,…
This study investigates malicious AI Assistants' manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making contexts. We also examine…
Autonomous coding agents are increasingly deployed as AI teammates in modern software engineering, independently authoring pull requests (PRs) that modify production code at scale. This study aims to systematically characterize how…
Third-party software, or skills, are essential components in Smart Personal Assistants (SPA). The number of skills has grown rapidly, dominated by a changing environment that has no clear business model. Skills can access personal…
LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which…
AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…
AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…
Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model (LLM) agents for tasks such as code review and data synchronization. While bringing convenience…
Malicious website detection is an increasingly relevant yet intricate task that requires the consideration of a vast amount of fine details. Our objective is to create a machine learning model that is trained on as many of these finer…
Agent Skills is an emerging open standard that defines a modular, filesystem-based packaging format enabling LLM-based agents to acquire domain-specific expertise on demand. Despite rapid adoption across multiple agentic platforms and the…
Large language model (LLM) agents increasingly rely on skills to package reusable capabilities through instructions, tools, and resources. High-quality skills embed expert knowledge, curated workflows, and execution constraints into agents,…
Different types of malicious activities have been flagged in multiple permissionless blockchains such as bitcoin, Ethereum etc. While some malicious activities exploit vulnerabilities in the infrastructure of the blockchain, some target its…
Agentic AI coding tools such as Claude Code and OpenAI Codex execute multi-step coding tasks with limited human oversight. To steer these tools, developers create repository-level configuration artifacts (e.g., Markdown files) for…
Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful…
As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical systems challenge. In small libraries, users may invoke skills explicitly by name, but this…
Large language models (LLMs) are increasingly being integrated into software development processes. The ability to generate code and submit pull requests with minimal human intervention, through the use of autonomous AI agents, is poised to…
In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user inadvertently installs the tool and the LLM agent selects it during task execution, the tool can compromise the user's security and…
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…