When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks

Abstract

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities improve automation and scalability, they also pose new security risks in multi-agent networks. Existing research has studied how individual LLM-based agents can be compromised through prompt injection, jailbreaking, poisoned retrieval data, or malicious extensi

Categories

Framework mappings

Suggested from the entry's categories.

@misc{cai2026when,
  title = {{When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks}},
  author = {Ziwen Cai and Yihe Zhang and Xiali Hei},
  year = {2026},
  month = may,
  eprint = {2605.08460},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.08460}
}