1
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
动态红队测试与集成感知防御：首个覆盖Gmail、Salesforce等主流SaaS集成的LLM Agent安全基准，揭示间接提示注入的真实威胁。
arXiv:2606.02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from i…