CVE-2024-6961
XXE in Guardrails AI when consuming RAIL documents
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- High
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- None
- Availability
- None
Exploit likelihood
What each source reports
CVE List Score used
XXE in Guardrails AI when consuming RAIL documents
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.
- Record
CVE-2024-6961- CVSS 3.1
- 5.9 Medium
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-611, CWE-611
- Updated
- 2026-11-02
EUVDEUVD-2024-2333
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.
- Record
EUVD-2024-2333- CVSS 3.1
- 5.9 Medium
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N - Updated
- 2026-11-03
GitHub AdvisoriesGHSA-f8hx-f4xw-c646
Guardrails AI vulnerable to Improper Restriction of XML External Entity Reference
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.
- Record
GHSA-f8hx-f4xw-c646- CVSS 4.0
- 8.2 High
CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N - CVSS 3.1
- 5.9 Medium
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-611
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2024-6961- CVSS 3.1
- 5.9 Medium
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-611
- Updated
- 2026-11-02
OSVGHSA-f8hx-f4xw-c646
Guardrails AI vulnerable to Improper Restriction of XML External Entity Reference
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.
- Record
GHSA-f8hx-f4xw-c646- CVSS 4.0
- 8.2 High
CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N - CVSS 3.1
- 5.9 Medium
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-611
- Updated
- 2026-11-02
OSVPYSEC-2026-1431
Guardrails AI vulnerable to Improper Restriction of XML External Entity Reference
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.
- Record
PYSEC-2026-1431- CVSS 4.0
- 8.2 High
CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N - CVSS 3.1
- 5.9 Medium
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N - Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
guardrails-aiPyPI |
before 0.5.0 | 0.5.0 |
guardrails-aiPyPI |
before 0.5.0, plus listed versions 0.1.00.1.0rc10.1.0rc20.1.0rc30.1.1 Show 45 moreShow less0.1.20.1.30.1.40.1.50.1.60.1.70.1.80.1.90.2.00.2.0a10.2.0a20.2.0a30.2.0a40.2.0a50.2.0a60.2.10.2.1a00.2.20.2.30.2.3a10.2.40.2.4a10.2.50.2.60.2.70.2.80.2.90.3.00.3.10.3.20.3.30.4.00.4.10.4.20.4.30.4.40.4.50.5.0a00.5.0a10.5.0a100.5.0a110.5.0a120.5.0a130.5.0a20.5.0a3 |
0.5.0 |
History
| Recorded | Changed | Sources |
|---|---|---|
| aliases, published | EUVD | |
| first indexed | CVE List, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2024-6961 is a medium vulnerability (CVSS 5.9) in Guardrailsai Guardrails, published July 21, 2024. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.41%, the 35th percentile. Fixed in guardrails-ai 0.5.0.
References
research.jfrog.com/vulnerabilities/guardrails-rail-xxe-jfsa-2024-001035519
nvd.nist.gov/vuln/detail/CVE-2024-6961
github.com/guardrails-ai/guardrails/pull/922
pypi.org/project/guardrails-ai
Left out here: 6 versions. The JSON record has them.