CVE-2024-6961: XXE in Guardrails AI when consuming RAIL documents

Severity: medium (CVSS 5.9 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.4% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2024-07-21 · updated 2026-06-17
Weakness: CWE-611

Description

RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from external sources are vulnerable to XXE, which may cause leakage of internal file data via the SYSTEM entity.

Affected products

Guardrailsai Guardrails: before 0.5.0 — fixed in 0.5.0

How to fix

Upgrade to a fixed version: Guardrailsai Guardrails 0.5.0. Check the vendor advisory for mitigations.

References

https://research.jfrog.com/vulnerabilities/guardrails-rail-xxe-jfsa-2024-001035519/
https://research.jfrog.com/vulnerabilities/guardrails-rail-xxe-jfsa-2024-001035519/

Get alerted when CVE-2024-6961 or the next vulnerability affects your stack