Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

Abstract

Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments. This transition changes the nature of security risk. In agentic settings, failures are no longer limited to unsafe text generation. Untrusted content may redirect control flow, misuse tool privileges, corrupt persistent state, leak sensitive information, or trigger harmful external actions. At the same time, researc

Categories

Framework mappings

Suggested from the entry's categories.

@misc{ling2026secure,
  title = {{Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation}},
  author = {Yuchen Ling and Shengcheng Yu and Zhenyu Chen and Chunrong Fang},
  year = {2026},
  month = jun,
  eprint = {2606.10749},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.10749}
}