paperAugust 2026Unreviewed

SkillShield: Prompt-Space Security Skills for LLM Coding Agents

Xiaodong Wu, Zhimin Zhao, Qi Li, Xiangman Li, Yu Shi, Bram Adams, Jianbing Ni

Abstract

A coding agent edits files and executes shell commands with its developer's privileges, allowing malicious requests to translate directly into harmful actions or functional malware. Existing defenses have complementary limitations: weight-level alignment is unavailable to API-only deployers, whereas input filters and execution-boundary monitors require auxiliary classification or checking components along the agent's trajectory. We therefore introduce SkillShield, a system-prompt defense that sy

Cite

@misc{wu2026skillshield,
  title = {{SkillShield: Prompt-Space Security Skills for LLM Coding Agents}},
  author = {Xiaodong Wu and Zhimin Zhao and Qi Li and Xiangman Li and Yu Shi and Bram Adams and Jianbing Ni},
  year = {2026},
  month = aug,
  eprint = {2608.25817},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.25817}
}