← Vulnerability feed

Vulnerability record · CVE-2026-40087 · published 9 April 2026

CVE-2026-40087: Langchain core vulnerability

Langchain · Langchain Core

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 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.

5.3 CVSS 3.1 Medium EPSS 0.45% · top 63.1% CWE-1336 · CWE-1336
5.3CVSS 3.1 base score
0.45%EPSS exploitation probability, 30 days
NoNot in CISA KEV
1Affected product versions listed by NVD
7References
17 Jun 2026Last modified by NVD

Description

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 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.

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Affected products

1 vulnerable configurations from NVD's CPE data, grouped by vendor and product.

References

LinkTags
https://github.com/langchain-ai/langchain/commit/6bab0ba3c12328008ddca3e0d54ff5a6151cd27b Patch
https://github.com/langchain-ai/langchain/commit/af2ed47c6f008cdd551f3c0d87db3774c8dfe258 Patch
https://github.com/langchain-ai/langchain/pull/36612 Issue TrackingPatch
https://github.com/langchain-ai/langchain/pull/36613 Issue TrackingPatch
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.84 ProductRelease Notes
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.28 ProductRelease Notes
https://github.com/langchain-ai/langchain/security/advisories/GHSA-926x-3r5x-gfhw MitigationVendor Advisory

Track CVE-2026-40087 inside VULONE

Watch it alongside the ransomware crews, C2 infrastructure and forum chatter that reference it, query it through the API and pull it into your SIEM over TAXII.

Start free Open in platform

Related vulnerabilities

Same products first, then exploited flaws of the same weakness class.

8.2CVE-2025-68664Langchain core deserialization of untrusted data vulnerabilityLangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerabilit…EPSS 43%7.5CVE-2026-34070Langchain core path traversal vulnerabilityLangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.load…EPSS 1.2%3.7CVE-2026-26013Langchain core server-side request forgery (ssrf) vulnerabilityLangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetc…EPSS 0.42%10.0CVE-2026-75650Adobe Commerce template engine flaw allows unauthenticated remote code executionAdobe Commerce, Commerce B2B and Magento are affected by improper neutralization of special elements used in a template engine (CWE-1336), allowing a…KEVEPSS 3.9%analysed9.8CVE-2024-23692Rejetto HTTP File Server template injection leads to unauthenticated RCERejetto HTTP File Server through version 2.3m is vulnerable to template injection, allowing a remote unauthenticated attacker to execute arbitrary co…KEVEPSS 99%analysed10.0CVE-2024-4040CrushFTP server-side template injection enables unauthenticated sandbox escape and RCECrushFTP versions before 10.7.1 and 11.1.0 contain a server-side template injection flaw that lets unauthenticated remote attackers escape the VFS sa…KEVEPSS 100%analysed

Source: NIST National Vulnerability Database (record CVE-2026-40087), CISA KEV, FIRST EPSS (scores of 2026-09-27). This page is refreshed as NVD updates the record.