# Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training > Source: > Published: 2026-10-07 05:00:02+00:00 Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker supplies a model with a backdoor: hidden behavior that produces malicious outputs when a particular input pattern appears. Focusing on software-engineering