Yi Nian

Agent Audit is a novel security analysis system that comprehensively audits LLM agent applications by examining the entire software stack—including tool code, configuration, and prompts—to detect a wide range of vulnerabilities.

This paper identifies and analyzes unintentional cross-user contamination (UCC), a failure mode where benign, scope-bound artifacts degrade the outcomes of different users in shared-state LLM agents, requiring artifact-level defenses.