LATIDIA · Ciberseguridad

SkillCODER: Hacia la auditoría y la atribución de la infracción de derechos de autor en las habilidades de agente de LLM

arXiv:2611.11308v1 Announce Type: new Abstract: Agent skills package reusable workflows and task-specific procedures into deployable natural-language artifacts for LLM agents. Su escala y legibilidad los hacen valiosos

La noticia

arXiv:2611.11308v1 Announce Type: new Abstract: Agent skills package reusable workflows and task-specific procedures into deployable natural-language artifacts for LLM agents. Their scale and readability make them valuable but vulnerable to unauthorized redistribution and repackaging. Existing prompt copyright auditing methods struggle with long skills and introduce token-level perturbations that compromise readability. We propose SkillCODER for copyright auditing and buyer attribution in a black-box, content-only setting. During embedding, SkillCODER parses a skill into a section-aware intermediate representation, SkillIR, to identify structural anchors. It distributes conditional instructions across these anchors to form an Artifact-Gated Capsule, designed to activate under verification queries and remain dormant otherwise. Controlled-Vocabulary Error-Correcting Codes encode buyer-specific fingerprints through controlled