CVE-2026-40087
Langchain Core ≤ 0.3.84
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:NSummary
CVE-2026-40087 is a medium-severity Improper Neutralization of Special Elements Used in a Template Engine (CWE-1336) vulnerability in Langchain Langchain Core. Its CVSS base score is 5.3 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique Template Injection (T1221); ranked at the 18th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as NLP and Transformers; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-21063
Vulnerability Data
LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangChain's f-string prompt-template validation was incomplete in two respects. First, some prompt template classes accepted f-string templates and formatted them without enforcing the same attribute-access…
more
validation as PromptTemplate. In particular, DictPromptTemplate and ImagePromptTemplate could accept templates containing attribute access or indexing expressions and subsequently evaluate those expressions during formatting. Second, f-string validation based on parsed top-level field names did not reject nested replacement fields inside format specifiers. In this pattern, the nested replacement field appears in the format specifier rather than in the top-level field name. As a result, earlier validation based on parsed field names did not reject the template even though Python formatting would still attempt to resolve the nested expression at runtime. This vulnerability is fixed in 0.3.84 and 1.2.28.
- CWE(s)
AI Security AnalysisAI
- AI Category
- NLP and Transformers
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- AI-specific weaknesses CR
- CWE-1427 — Incomplete f-string validation in LLM prompt templates allows unsafe expressions during formatting.
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.- Classification Reason
- Matched keywords: langchain, llm
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.2V1.3.7V1.3.10
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and static analysis can discover missing neutralization of template directives.
Input validation rejects or sanitizes untrusted data before it reaches the template engine, stopping injection of special syntax.
Security engineering principles require use of safe templating APIs and proper escaping of external input.
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.
Secure SDLC practices directly require proper input neutralization in template engines to prevent injection.
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.
Security testing can detect template-injection flaws but does not itself implement neutralization controls.
Secure development life cycle mandates input validation and sanitization that directly prevents template-injection weaknesses.
Application security requirements explicitly call for neutralizing special elements in template engines.
Secure architecture principles reduce the likelihood of unsafe template processing but do not prescribe specific neutralization techniques.
Secure coding standards require proper escaping or sandboxing of template directives, directly mitigating CWE-1336.