guardrail-rs A Fail-Open Reverse Proxy for Prompt-Injection Defense and PII Redaction in LLM Applications

Abstract

Abstract Applications built on large language models (LLMs) typically forward user input to a model provider with no enforcement layer in between, leaving prompt-injection attempts and personally identifiable information (PII) to pass through unfiltered in both directions. We present guardrail-rs, an open-source reverse proxy, implemented in Rust, that sits between an application and its LLM provider and inspects every request and response before it crosses the network boundary. The system is bu

Categories

Framework mappings

Suggested from the entry's categories.

@misc{myet2026guardrailrs,
  title = {{guardrail-rs A Fail-Open Reverse Proxy for Prompt-Injection Defense and PII Redaction in LLM Applications}},
  author = {Min Htet Myet},
  year = {2026},
  month = jul,
  doi = {10.21203/rs.3.rs-10354224/v1},
  url = {https://doi.org/10.21203/rs.3.rs-10354224/v1}
}