Related papers: Demystifying and Detecting Agentic Workflow Inject…
As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…
Agentic AI coding editors driven by large language models have recently become more popular due to their ability to improve developer productivity during software development. Modern editors such as Cursor are designed not just for code…
AI Agents have rapidly gained prominence in both research and industry as systems that extend large language models with planning, tool use, memory, and goal-directed action. Despite this progress, the development and maintenance of Agent…
Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…
Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant operational expense,…
Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…
Previous benchmarks on prompt injection in large language models (LLMs) have primarily focused on generic tasks and attacks, offering limited insights into more complex threats like data exfiltration. This paper examines how prompt…
The widespread availability of open-source repositories has led to a vast collection of reusable software components, yet their utilization remains manual, error-prone, and disconnected. Developers must navigate documentation, understand…
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…
Actionable Warning Identification (AWI) plays a crucial role in improving the usability of static code analyzers. With recent advances in Machine Learning (ML), various approaches have been proposed to incorporate ML techniques into AWI.…
Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly…
Large language model (LLM) agents increasingly rely on external tools and retrieval systems to autonomously complete complex tasks. However, this design exposes agents to indirect prompt injection (IPI), where attacker-controlled context…
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…
Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions…
We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written tests. Given a set of tests, TDFlow repeatedly proposes,…
In recent years, agentic artificial intelligence (AI) systems are becoming increasingly widespread. These systems allow agents to use various tools, such as web browsers, compilers, and more. However, despite their popularity, agentic AI…
With the fast development of large language models (LLMs), LLM-driven Web Agents (Web Agents for short) have obtained tons of attention due to their superior capability where LLMs serve as the core part of making decisions like the human…
The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web…
Static benchmarks measure what AI agents can do at a fixed point in time but not how they are adopted, maintained, or experienced in deployment. We introduce AgentPulse, a continuous evaluation framework scoring 50 agents across 10 workload…
AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…