PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts

arXiv:2605.05974v1 Announce Type: cross Abstract: LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments, adversaries can copy and reuse these prompts with other proprietary...