相关论文: SkillScanner: Detecting Policy-Violating Voice App…

Online code clones are code fragments that are copied from software projects or online sources to Stack Overflow as examples. Due to an absence of a checking mechanism after the code has been copied to Stack Overflow, they can become toxic…

Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines. Skills execute with user privileges and are distributed through community registries with minimal vetting, but no…

Does the training of large language models potentially infringe upon code licenses? Furthermore, are there any datasets available that can be safely used for training these models without violating such licenses? In our study, we assess the…

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites…

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…

Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…

Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks…

We present Alexa versus Alexa (AvA), a novel attack that leverages audio files containing voice commands and audio reproduction methods in an offensive fashion, to gain control of Amazon Echo devices for a prolonged amount of time. AvA…

While scaling laws for Large Language Models (LLMs) have been extensively studied along dimensions of model parameters, training data, and compute, the scaling behavior of LLM-based educational agents remains unexplored. We propose that…

We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security…

While Alexa can perform over 100,000 skills on paper, its capability covers only a fraction of what is possible on the web. To reach the full potential of an assistant, it is desirable that individuals can create skills to automate their…

New contributors often struggle to find tasks that they can tackle when onboarding onto a new Open Source Software (OSS) project. One reason for this difficulty is that issue trackers lack explanations about the knowledge or skills needed…

Hundreds of millions of people now regularly interact with large language models via chatbots. Model developers are eager to acquire new sources of high-quality training data as they race to improve model capabilities and win market share.…

Users often interpret and select agent skills through their SKILL markdown specifications. To protect users, existing audits mainly focus on malicious or unsafe skills. We study the complementary question of whether specifications help…

Developers rely on third-party library Application Programming Interfaces (APIs) when developing software. However, libraries typically come with assumptions and API usage constraints, whose violation results in API misuse. API misuses may…

This paper presents a large-scale analysis of fingerprinting-like behavior in the mobile application ecosystem. We take a market-based approach, focusing on third-party tracking as enabled by applications' common use of third-party SDKs.…

We performed two online surveys of Stack Overflow answerers and visitors to assess their awareness to outdated code and software licenses in Stack Overflow answerers. The answerer survey targeted 607 highly reputed Stack Overflow users and…

Graphs of developer networks are important for software engineering research and practice. For these graphs to realistically represent the networks, accurate developer identities are imperative. We aim to identify developer identity errors…