论文 EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents
论文 An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios
论文 Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response
论文 Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
论文 AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents
论文 Token-Flow Firewall: Semantic Runtime Auditing for Persistent AI Agents