CVE-2025-46726
Published: 05 May 2025
Summary
CVE-2025-46726 is a high-severity Improper Restriction of XML External Entity Reference (CWE-611) vulnerability in Langroid Langroid. Its CVSS base score is 7.8 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Data from Local System (T1005); ranked in the top 36.1% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as NLP and Transformers; in the LLM/Generative AI Risks risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-13410
Vulnerability details
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…
more
the issue.
- CWE(s)
AI Security AnalysisAI
- AI Category
- NLP and Transformers
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: llm
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
XML vulnerability enables local file disclosure (T1005: Data from Local System) and DoS via resource exhaustion such as entity expansion (T1499: Endpoint Denial of Service).
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.