Related papers: Demystifying and Detecting Agentic Workflow Inject…
Developers often struggle with maintaining GitHub Actions workflow configurations in GitHub-hosted repositories, with recent studies showing frequent execution failures. This paper empirically explores how the adoption and evolution of…
AI agents that build user interfaces on the fly assembling buttons, forms, and data displays from structured protocol payloads are becoming common in production systems. The trouble is that a payload can pass every schema check and still…
Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…
Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform…
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…
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…
As large language models increasingly deployed into agentic systems, existing methods face critical gaps in observing, assessing, and mitigating deployment-specific risks. We present a comprehensive, observability-driven workflow: we…
LLM-based agents are increasingly deployed for software maintenance tasks such as automated program repair (APR). APR agents automatically fetch GitHub issues and use backend LLMs to generate patches that fix the reported bugs. However,…
The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…
Modern software infrastructure increasingly relies on LLM agents for development and maintenance, such as Claude Code and Gemini-cli. However, these AI agents differ fundamentally from traditional deterministic software, posing a…
Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…
Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching…
Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hinder reliability and maintainability. Unlike traditional…
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…
Crash narratives in crash reports provide crucial contextual information for traffic safety analysis. Yet, their broader use is hindered by the presence of personally identifiable information (PII), including names, home addresses, and…
Autonomous AI agents extend large language models into full runtime systems that load skills, ingest external content, maintain memory, plan multi-step actions, and invoke privileged tools. In such systems, security failures rarely remain…
Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…
Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…