AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

Abstract

Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Existing benchmarks under-measure the threat: most cover only a handful of integrations with the same attack payload replayed across runs, and open-source guards are trained on chat-style data rather than tool-response content. We introduce

Categories

Framework mappings

Suggested from the entry's categories.

@misc{dingeto2026agentredbench,
  title = {{AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations}},
  author = {Hiskias Dingeto and William Leeney},
  year = {2026},
  month = jun,
  eprint = {2606.02240},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.02240}
}