CVE-2026-40087: Langchain core LangChain Has Incomplete F-string Validation Vulnerability

MODERATE
Advisory Identifier: GHSA-926x-3r5x-gfhw
CVSS 5.3
CWE-20 CWE-1336
Published
Advisory Summary

CVE-2026-40087 is a MODERATE (CVSS 5.3) langchain has incomplete f-string validation vulnerability (CWE-20: Improper Input Validation) affecting Langchain core libraries in the PyPI ecosystem. The issue involves langchain has incomplete f-string validation in prompt templates. Remediation is available by upgrading affected packages to version 0.3.84, 1.2.28.

CVE-2026-40087 at a Glance

CVE Identifier CVE-2026-40087
GHSA Identifier GHSA-926x-3r5x-gfhw
Severity MODERATE
CVSS v3.1 Base Score 5.3
CWE Classification CWE-20: Improper Input Validation
Affected Product Langchain core
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 5.3

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required None (PR:N)
User Interaction None (UI:N)
Scope Unchanged (S:U)
Confidentiality Low (C:L)
Integrity None (I:N)
Availability None (A:N)

How to Fix CVE-2026-40087

To remediate this vulnerability, upgrade all affected Langchain core dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

langchain-core fixed: 0.3.84
pip install langchain-core>=0.3.84
langchain-core fixed: 1.2.28
pip install langchain-core>=1.2.28
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release:

pip show langchain-core

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2026-40087, inspect your installed packages using pip:

pip show langchain-core

Analyze the terminal output to locate any version of Langchain core in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 0.3.84), your application is affected.

Note: The pip show langchain-core command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-20: Improper Input Validation, where the product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly. In Langchain core, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

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. Examples of the affected shape include: ```python "{message.additional_kwargs[secret]}" "https://example.com/{image.__class__.__name__}.png" ``` Second, f-string validation based on parsed top-level field names did not reject nested replacement fields inside format specifiers. For example: ```python "{name:{name.__class__.__name__}}" ``` 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. ## Affected usage This issue is only relevant for applications that accept untrusted template strings, rather than only untrusted template variable values. In addition, practical impact depends on what objects are passed into template formatting: - If applications only format simple values such as strings and numbers, impact is limited and may only result in formatting errors. - If applications format richer Python objects, attribute access and indexing may interact with internal object state during formatting. In many deployments, these conditions are not commonly present together. Applications that allow end users to author arbitrary templates often expose only a narrow set of simple template variables, while applications that work with richer internal Python objects often keep template structure under developer control. As a result, the highest-impact scenario is plausible but is not representative of all LangChain applications. Applications that use hardcoded templates or that only allow users to provide variable values are not affected by this issue. ## Impact The direct issue in `DictPromptTemplate` and `ImagePromptTemplate` allowed attribute access and indexing expressions to survive template construction and then be evaluated during formatting. When richer Python objects were passed into formatting, this could expose internal fields or nested data to prompt output, model context, or logs. The nested format-spec issue is narrower in scope. It bypassed the intended validation rules for f-string templates, but in simple cases it results in an invalid format specifier error rather than direct disclosure. Accordingly, its practical impact is lower than that of direct top-level attribute traversal. Overall, the practical severity depends on deployment. Meaningful confidentiality impact requires attacker control over the template structure itself, and higher impact further depends on the surrounding application passing richer internal Python objects into formatting. ## Fix The fix consists of two changes. First, LangChain now applies f-string safety validation consistently to `DictPromptTemplate` and `ImagePromptTemplate`, so templates containing attribute access or indexing expressions are rejected during construction and deserialization. Second, LangChain now rejects nested replacement fields inside f-string format specifiers. Concretely, LangChain validates parsed f-string fields and raises an error for: - variable names containing attribute access or indexing syntax such as `.` or `[]` - format specifiers containing `{` or `}` This blocks templates such as: ```python "{message.additional_kwargs[secret]}" "https://example.com/{image.__class__.__name__}.png" "{name:{name.__class__.__name__}}" ``` The fix preserves ordinary f-string formatting features such as standard format specifiers and conversions, including examples like: ```python "{value:.2f}" "{value:>10}" "{value!r}" ``` In addition, the explicit template-validation path now applies the same structural f-string checks before performing placeholder validation, ensuring that the security checks and validation checks remain aligned.

CVE-2026-40087 Affected Langchain core Versions

2 component(s)
Fixed Versions:
0.3.841.2.28
Product / Package Ecosystem Affected Versions Fixed Version
langchain-core
PyPI
< 0.3.84
0.3.84
langchain-core
PyPI
≥ 1.0.0a1
< 1.2.28
1.2.28

References

Frequently Asked Questions

What is CVE-2026-40087?
CVE-2026-40087 is a security vulnerability in Langchain core involving LangChain has incomplete f-string validation in prompt templates under CWE-20: Improper Input Validation.
Which Langchain core versions are affected?
Affected versions include releases prior to 0.3.84, 1.2.28 across affected packages: langchain-core.
What version fixes CVE-2026-40087?
Upgrading to 0.3.84, 1.2.28 (or the latest patched release for your respective branch) resolves the vulnerability.
Is langchain-core affected?
Yes, langchain-core is affected in releases prior to 0.3.84, 1.2.28. Upgrade your dependency to 0.3.84, 1.2.28 or later.
What is the CVSS score of CVE-2026-40087?
CVE-2026-40087 has a CVSS v3.1 base score of 5.3 (MODERATE) with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N.
What CWE is associated with CVE-2026-40087?
CVE-2026-40087 is classified under CWE-20: Improper Input Validation (The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.).
How can I check PyPI dependencies for CVE-2026-40087?
Run the dependency tree command: 'pip show langchain-core'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-926x-3r5x-gfhw",
  "modified" : "2026-04-10T14:41:45Z",
  "published" : "2026-04-08T21:51:32Z",
  "aliases" : [ "CVE-2026-40087" ],
  "summary" : "LangChain has incomplete f-string validation in prompt templates",
  "details" : "LangChain's f-string prompt-template validation was incomplete in two respects.\n\nFirst, 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.\n\nExamples of the affected shape include:\n\n```python\n\"{message.additional_kwargs[secret]}\"\n\"https://example.com/{image.__class__.__name__}.png\"\n```\n\nSecond, f-string validation based on parsed top-level field names did not reject nested replacement fields inside format specifiers. For example:\n\n```python\n\"{name:{name.__class__.__name__}}\"\n```\n\nIn 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.\n\n## Affected usage\n\nThis issue is only relevant for applications that accept untrusted template strings, rather than only untrusted template variable values.\n\nIn addition, practical impact depends on what objects are passed into template formatting:\n\n- If applications only format simple values such as strings and numbers, impact is limited and may only result in formatting errors.\n- If applications format richer Python objects, attribute access and indexing may interact with internal object state during formatting.\n\nIn many deployments, these conditions are not commonly present together. Applications that allow end users to author arbitrary templates often expose only a narrow set of simple template variables, while applications that work with richer internal Python objects often keep template structure under developer control. As a result, the highest-impact scenario is plausible but is not representative of all LangChain applications.\n\nApplications that use hardcoded templates or that only allow users to provide variable values are not affected by this issue.\n\n## Impact\n\nThe direct issue in `DictPromptTemplate` and `ImagePromptTemplate` allowed attribute access and indexing expressions to survive template construction and then be evaluated during formatting. When richer Python objects were passed into formatting, this could expose internal fields or nested data to prompt output, model context, or logs.\n\nThe nested format-spec issue is narrower in scope. It bypassed the intended validation rules for f-string templates, but in simple cases it results in an invalid format specifier error rather than direct disclosure. Accordingly, its practical impact is lower than that of direct top-level attribute traversal.\n\nOverall, the practical severity depends on deployment. Meaningful confidentiality impact requires attacker control over the template structure itself, and higher impact further depends on the surrounding application passing richer internal Python objects into formatting.\n\n## Fix\n\nThe fix consists of two changes.\n\nFirst, LangChain now applies f-string safety validation consistently to `DictPromptTemplate` and `ImagePromptTemplate`, so templates containing attribute access or indexing expressions are rejected during construction and deserialization.\n\nSecond, LangChain now rejects nested replacement fields inside f-string format specifiers.\n\nConcretely, LangChain validates parsed f-string fields and raises an error for:\n\n- variable names containing attribute access or indexing syntax such as `.` or `[]`\n- format specifiers containing `{` or `}`\n\nThis blocks templates such as:\n\n```python\n\"{message.additional_kwargs[secret]}\"\n\"https://example.com/{image.__class__.__name__}.png\"\n\"{name:{name.__class__.__name__}}\"\n```\n\nThe fix preserves ordinary f-string formatting features such as standard format specifiers and conversions, including examples like:\n\n```python\n\"{value:.2f}\"\n\"{value:>10}\"\n\"{value!r}\"\n```\n\nIn addition, the explicit template-validation path now applies the same structural f-string checks before performing placeholder validation, ensuring that the security checks and validation checks remain aligned.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "langchain-core"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "0.3.84"
      } ]
    } ],
    "database_specific" : {
      "last_known_affected_version_range" : "< 0.3.83"
    }
  }, {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "langchain-core"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "1.0.0a1"
      }, {
        "fixed" : "1.2.28"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/security/advisories/GHSA-926x-3r5x-gfhw"
  }, {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-40087"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/pull/36612"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/pull/36613"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/commit/6bab0ba3c12328008ddca3e0d54ff5a6151cd27b"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/commit/af2ed47c6f008cdd551f3c0d87db3774c8dfe258"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/langchain-ai/langchain"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.84"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.28"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-1336", "CWE-20" ],
    "severity" : "MODERATE",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-04-08T21:51:32Z",
    "nvd_published_at" : "2026-04-09T20:16:27Z"
  }
}