[new-research] arXiv:2608.27990 — CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Inject

[github-actions]

New arXiv Research Paper

arXiv ID: 2608.27990
Title: CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?
Authors: Zi Liang, Xiaoyu Xu, Yanyun Wang, Minxin Du, Qingqing Ye, Haibo Hu
Published: 2026-08-28T06:58:26Z
URL: https://arxiv.org/abs/2608.27990

Abstract (first 300 chars)

Prompt injection attacks on Large Language Model (LLM) agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underlying LLMs to execute harmful actions outside their benign scope. While current defenses effectively counter known inject…

Suggested OWASP Mapping

LLM01, ASI01, ASI02

Suggested Action

Review this paper against the OWASP GenAI Crosswalk entries and update relevant mapping files if new attack patterns or mitigations are identified.