Related papers: Formal Analysis and Supply Chain Security for Agen…
Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential…
Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid…
Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill…
Although large language model (LLM)-based agents, exemplified by OpenClaw, are increasingly evolving from task-oriented systems into personalized AI assistants for solving complex real-world tasks, their practical deployment also introduces…
The Model Context Protocol (MCP), introduced by Anthropic in November 2024 and now governed by the Linux Foundation's Agentic AI Foundation, has rapidly become the de facto standard for connecting large language model (LLM)-based agents to…
Agent frameworks increasingly encode tool-using behavior as explicit workflow graphs, yet safety enforcement remains a runtime concern. These frameworks expose analyzable graph structure through their APIs, enabling pre-deployment static…
Modern generative agents such as OpenClaw - an open-source, self-hosted personal assistant with a community skill ecosystem, are gaining attention and are used pervasively. However, the openness and rapid growth of these ecosystems often…
Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…
GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…
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…
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current…
Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…
EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…
Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…
Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents…
Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct…
LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it…
We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public…
Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating…