Read the docs
TI-2024-06460 Aliases CVE-2024-6961GHSA-f8hx-f4xw-c646

XXE in Guardrails AI when consuming RAIL documents

Priority MEDIUM 60CWE-611Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
High
Impact type
Information disclosure
Confidentiality · integrity · availability
High · None · None
Fix status
Fixed

Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub. Impact type from CWE-611 and the CVSS impact.

Summary

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00408 35th percentileScored 2026-11-07
Fix Fixed guardrails-ai: 0.5.0guardrails-ai (PyPI): 0.5.0

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
—guardrails-aibefore 0.5.00.5.0Patch availableCNA
—guardrails-ai (PyPI)before 0.5.00.5.0Patch availableGHSA-f8hx-f4xw-c646
  • guardrails-ai Vendor— Affected before 0.5.0 Fixed in 0.5.0 Patch available CNA
  • guardrails-ai (PyPI) Vendor— Affected before 0.5.0 Fixed in 0.5.0 Patch available GHSA-f8hx-f4xw-c646

CPE names CISA-ADP · 1

CPEVersionsRoleVendor
cpe:2.3:a:guardrailsai:guardrails:*:*:*:*:*:*:*:*——Guardrails AI
  • cpe:2.3:a:guardrailsai:guardrails:*:*:*:*:*:*:*:* Versions — — ·Guardrails AI

Remediation

  • Fix · CNA guardrails-ai Fixed in 0.5.0
  • Fix · GHSA-f8hx-f4xw-c646 guardrails-ai (PyPI) Fixed in 0.5.0 Advisory →

Timeline

  1. 2026-10-02 Threatist record created from CVE-2024-6961
  2. 2026-10-03 Alias added: GHSA-f8hx-f4xw-c646

References

Sources