← all papers · overview

No Attacker Needed: Unintentional Cross-user Contamination In Shared-state LLM Agents

Abstract

LLM-based agents increasingly operate across repeated sessions, maintaining task states to ensure continuity. In many deployments, a single agent serves multiple users within a team or organization, reusing a shared knowledge layer across user identities. This shared persistence expands the failure surface: information that is locally valid for one user can silently degrade another user's outcome

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).