8 papers
Towards a Risk Assessment of Malicious Skill Files in Coding Agents
Rui Yang, Michael Fu, Kla Tantithamthavorn +2
Autonomous coding agents are increasingly embedded in enterprise software workflows with delegated authority over connected systems. Central to this architecture is the agent skill…
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents
Rui Yang, Michael Fu, Kla Tantithamthavorn +2
Software engineering teams now deploy AI coding agents (Cursor, Claude Code, GitHub Copilot) as first-class productivity tools, installing domain-specific skill files to tailor age…
CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
Yuxi Chen, Haoyu Zhai, Chenkai Wang +4
GUI agents are rapidly shifting from multi-module pipelines to end-to-end, native vision-language models (VLMs) that perceive raw screenshots and directly interact with digital dev…
Robust, Observable, and Evolvable Agentic Systems Engineering: A Principled Framework Validated via the Fairy GUI Agent
Jiazheng Sun, Ruimeng Yang, Xu Han +5
The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these defic…
DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems
Rui Yang, Michael Fu, Chakkrit Tantithamthavorn +3
Intelligent software systems powered by Large Language Models (LLMs) are increasingly deployed in critical sectors, raising concerns about their safety during runtime. Through an i…
AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software
Rui Yang, Michael Fu, Chakkrit Tantithamthavorn +3
Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces…