Preliminary research

CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection

Qichen Zhao, Shengfang Zhai, Qingni Shen, Zhonghai Wu and Jiaheng Zhang · arXiv · 14 October 2026

AI-collected research leads through 3 November 2026, including a November–October–September missed-article review and a targeted multilingual search alongside earlier community-source sweeps. Unranked, incomplete, not community-vetted, and subject to change.

CoRedSkill distributes unauthorized operations across functioning agent skills using stage-specific AST rewrites and intermediate task artifacts. Its benchmark jointly checks legitimate task outputs, unauthorized effects, and audit detection.

Record

Researcher

Qichen Zhao, Shengfang Zhai, Qingni Shen, Zhonghai Wu and Jiaheng Zhang

Published by

arXiv

Date

14 October 2026

In the archive

• Collected in the 2026 preliminary research sweep

Tags

• ai-agent
• skills
• supply-chain
• code-injection
• methodology
• owasp-a06-2021

This page is the archive's own catalogue record. The research is the work of Qichen Zhao, Shengfang Zhai, Qingni Shen, Zhonghai Wu and Jiaheng Zhang, first published at the original source. Preserved copies are kept so the citation survives its host.