CVE-2025-46726 json
Langroid Vulnerable to XXE Injection via XMLToolMessage
published last yr. modified 4mo ago also EUVD-2025-13410 , GHSA-pw95-88fg-3j6f , PYSEC-2026-1532
- cvss
- 9.1
- version 3.1, NVD
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.7%
- EPSS 0.7% chance of exploitation in 30 days, percentile 51%
- public exploits
- 0
- none known
Summary
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.53.4, a LLM application leveraging `XMLToolMessage` class may be exposed to untrusted XML input that could result in DoS and/or exposing local files with sensitive information. Version 0.53.4 fixes the issue.
Patch / fix
Is CVE-2025-46726 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- partial
- Assessed
- last yr.
Exploit prediction
0.66% chance of exploitation in the next 30 days, higher than 51% of all scored CVEs (FIRST EPSS, 2026-11-09).
Exploits and checks
- github.com https://github.com/langroid/langroid/security/advisories/GHSA-pw95-88fg-3j6f referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 7.8 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:H/SC:N/SI:N/SA:N/E:P |
| CNA | 4.0 | 7.8 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:H/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| NVD | 3.1 | 9.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | langroid | <0.53.4 |
0.53.4 |
Affected products
- langroid langroid
Classification
- Weakness
-
- CWE-611 Improper Restriction of XML External Entity Reference
References
-
github.com
/langroid/langroid/commit/36e7e7db4dd1636de225c2c66c84052b1e9ac3c3
web, patch
-
github.com
/langroid/langroid/security/advisories/GHSA-pw95-88fg-3j6f
web, exploit, vendor-advisory
-
github.com
/langroid/langroid/blob/df6227e6c079ec22bb2768498423148d6685acff/langroid/agent/xml_tool_message.py#L51-L52
web, product
-
nvd.nist.gov
/vuln/detail/CVE-2025-46726
advisory
-
github.com
/langroid/langroid
package
-
pypi.org
/project/langroid
package
-
github.com
/advisories/GHSA-pw95-88fg-3j6f
advisory
Sources
- CVE List CVE-2025-46726
- GitHub Advisory GHSA-pw95-88fg-3j6f
- NVD CVE-2025-46726
- OSV PYSEC-2026-1532
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.