Established 2026Monday, 20 July 2026
presents

The CloudySec Digest

The wires, edited.
← Front PageAI Security Desk
AI Security

RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations

Enterprise RAG implementations face a novel supply chain risk where malicious actors could inject invisible Unicode characters into knowledge bases to trigger code execution.

Summary written by editorial AI · Source link below

Filed by arXiv Crypto & Security1 min readRead at source ↗

arXiv:2510.11195v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the need for model retraining. It does so by adding external data into the LLM's context. We develop a new class of black-box attack, RAG-Pull, that inserts hidden UTF characters into queries or external code repositories, redirecting retrieval toward malicious code, thereby breaking the models' safety

Continue at the source
Read the full report at arXiv Crypto & Security

External link — opens at arXiv Crypto & Security in a new tab.

§
Continue with

More from the AI Security Desk