paperMay 2026Unreviewed

OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing

Jianming Chen, Yawen Wang, Junjie Wang, Zhe Liu, Qing Wang, Fanjiang Xu

Abstract

Tool-calling text-to-image (T2I) agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool orchestration, where individually benign steps combine into unsafe results, making prompt-only jailbreak techniques insufficient. We present OrchJail, an orchestration-guided fuzzing framework for jailbreaking tool-calling T2I agents. Its core idea is to exploi

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{chen2026orchjail,
  title = {{OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing}},
  author = {Jianming Chen and Yawen Wang and Junjie Wang and Zhe Liu and Qing Wang and Fanjiang Xu},
  year = {2026},
  month = may,
  eprint = {2605.07414},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.07414}
}