{"ID":6536101,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-15T01:50:16.627184149Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10534","arxiv_id":"2607.10534","title":"Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach","abstract":"Large language model (LLM) agents are increasingly extended through Agent Skills, reusable artifacts that package natural-language metadata, procedural instructions, and execution-time resources for runtime use. As open-source skill marketplaces expand, users and agents increasingly rely on brief metadata to select third-party skills, making it difficult to detect inconsistencies between a skill's description and its true behavior, a problem we call cross-layer misalignment. To address this issue, we propose Progressive Loading-Aware Hierarchical Contrastive Learning (PL-HCL), an LLM-based framework that detects misalignment by modeling the layered structure of Agent Skills and learning cross-layer consistency. Using a normalized corpus of over 264,000 open-source skills and a human-verified challenge set, PL-HCL improves Macro-F1 from approximately 0.45 for unadapted baselines to 0.87-0.89 across evaluated LLM backbones. This approach offers an effective screening tool for users and operators, as well as design principles for detecting inconsistencies in layered digital artifacts.","short_abstract":"Large language model (LLM) agents are increasingly extended through Agent Skills, reusable artifacts that package natural-language metadata, procedural instructions, and execution-time resources for runtime use. As open-source skill marketplaces expand, users and agents increasingly rely on brief metadata to select thi...","url_abs":"https://arxiv.org/abs/2607.10534","url_pdf":"https://arxiv.org/pdf/2607.10534v1","authors":"[\"Chengjun Zhang\",\"Yang Gao\",\"Jianna Hur\",\"Jingjing Zhang\",\"Sagar Samtani\"]","published":"2026-07-12T02:07:37Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CR\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}