Related papers: Malicious Or Not: Adding Repository Context to Age…
While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…
Autonomous AI agents can now programmatically hire human workers through marketplaces using REST APIs and Model Context Protocol (MCP) integrations. This creates an attack surface analogous to CAPTCHA-solving services but with…
GitHub plays a critical role in modern software supply chains, making its security an important research concern. Existing studies have primarily focused on CI/CD automation, collaboration patterns, and community management, while abuse…
Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both…
Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that couples executable scripts, with non-executable guidance on…
Malicious software packages in open-source ecosystems, such as PyPI, pose growing security risks. Unlike traditional vulnerabilities, these packages are intentionally designed to deceive users, making detection challenging due to evolving…
Modern scientific ecosystems are rich in procedural knowledge across repositories, APIs, scripts, notebooks, documentation, databases, and papers, yet much of this knowledge remains fragmented across heterogeneous artifacts that agents…
Large language model (LLM) based coding agents increasingly act as autonomous contributors that generate and merge pull requests, yet their real-world effects on software projects are unclear-especially compared with widely adopted…
Language models (LMs) are increasingly used in collaboration: multiple LMs trained by different parties collaborate through routing systems, multi-agent debate, model merging, and more. Critical safety risks remain in this decentralized…
Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is…
The rise in the adoption of blockchain technology has led to increased illegal activities by cyber-criminals costing billions of dollars. Many machine learning algorithms are applied to detect such illegal behavior. These algorithms are…
LLM agents increasingly rely on reusable skill libraries, but these skills silently decay as the external services, packages, APIs, and configurations they reference evolve. Existing monitors detect such changes at the wrong granularity:…
LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with…
According to GitGuardian's monitoring of public GitHub repositories, the exposure of secrets (API keys and other credentials) increased two-fold in 2021 compared to 2020, totaling more than six million secrets. However, no benchmark dataset…
OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of…
Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for…
The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build integrity mechanisms cannot be used anymore. The available frameworks like SLSA, SBOM and in…
AI agents -- systems that execute multi-step reasoning workflows with persistent state, tool access, and specialist skills -- represent a qualitative shift from prior automation technologies in social science. Unlike chatbots that respond…
Today's AI agents are built on large language models (LLMs) equipped with tools to access and modify external environments, such as corporate file systems, API-accessible platforms and websites. AI agents offer the promise of automating…
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…