CVE-2024-1455
Langchain 0.1.4 – 0.1.35
Raw vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:HCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2024-1455 is a medium-severity XML Entity Expansion (CWE-776) vulnerability in Langchain Langchain. Its CVSS base score is 5.9 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique NTDS (T1003.003); ranked in the top 46% 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 LLM Application Platforms; in the Other ATLAS/OWASP Terms risk domain.
The strongest mitigations our analysis identified map to CM-6 (Configuration Settings) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2024-0987
Vulnerability Data
A vulnerability in the langchain-ai/langchain repository allows for a Billion Laughs Attack, a type of XML External Entity (XXE) exploitation. By nesting multiple layers of entities within an XML document, an attacker can cause the XML parser to consume excessive…
more
CPU and memory resources, leading to a denial of service (DoS).
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- Other ATLAS/OWASP Terms
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- LangChain (langchain-ai/langchain) is a framework for building applications with LLMs, including AI agents, chains, and integrations with language models, tools, and external services.
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Secure configuration settings can disable DTD processing or cap entity expansion in XML parsers.
Input validation can enforce limits on XML entity expansion and recursion depth before parsing occurs.
Least-functionality configuration can prohibit unsafe DTD features or external entity resolution.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Identifying and recording vulnerabilities can discover XML entity expansion flaws before exploitation.
Hardened configuration baselines can disable or limit DTD entity expansion in XML parsers.
Secure SDLC practices directly prevent introduction of improper recursive entity handling in XML code.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Secure SDLC mandates input validation and parser hardening that can prevent unbounded entity expansion.
Application security requirements can explicitly call for limits on XML entity recursion and DTD processing.
A.8.27 mandates security-by-design principles (defense-in-depth, least privilege, distrust external input, fail securely, hardening, design review against attack patterns) that reach some but not most instances of unsafe DTD entity expansion; the dominant fix is explicit parser configuration or entity limits, which the clause names only as one possible output of its broader process.
Secure coding standards directly require disabling or restricting recursive entity references in XML parsers.
Security testing can detect and block XML entity-expansion vulnerabilities before deployment.