Skip to content
Sagan

Paper

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Unreadunread

AI summary

arXiv:2606. 12737v1 Announce Type: new Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources.