A vulnerability in langchain-core versions >=0.1.17,<0.1.53, >=0.2.0,<0.2.43, and >=0.3.0,<0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability to create langchain_core.prompts.ImagePromptTemplate's (and by extension langchain_core.prompts.ChatPromptTemplate's) with input variables that can read any user-specified path from the server file system. If the outputs of these prompt templates are exposed to the user, either directly or through downstream model outputs, it can lead to the exposure of sensitive information.

Metrics

No CVSS v4.0

No CVSS v3.1

Attack Vector Network

Attack Complexity Low

Privileges Required None

Scope Unchanged

Confidentiality Impact Low

Integrity Impact None

Availability Impact None

User Interaction None

No CVSS v2

This CVE is not in the KEV list.

The EPSS score is 0.00068.

Exploitation poc

Automatable yes

Technical Impact partial

Affected Vendors & Products

Vendors Products
Langchain-ai Subscribe
Langchain Subscribe

No data.

No data.

OpenCVE Enrichment is a feature of OpenCVE that uses AI to automatically link vendors and products to CVEs. Learn more on GitHub.

Vendors Products
Langchain-ai Subscribe
Langchain Subscribe
Advisories
Source ID Title
EUVD EUVD EUVD-2025-7069 langchain-core allows unauthorized users to read arbitrary files from the host file system
Github GHSA Github GHSA GHSA-5chr-fjjv-38qv langchain-core allows unauthorized users to read arbitrary files from the host file system
Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

References
Link Providers
https://github.com/langchain-ai/langchain/commit/c1e742347f9701aadba8920e4d1f79a636e50b68 cve-icon cve-icon cve-icon
https://huntr.com/bounties/be1ee1cb-2147-4ff4-a57b-b6045271cf27 cve-icon cve-icon cve-icon
https://nvd.nist.gov/vuln/detail/CVE-2024-10940 cve-icon
https://www.cve.org/CVERecord?id=CVE-2024-10940 cve-icon
History

Fri, 21 Mar 2025 14:30:00 +0000

Type Values Removed Values Added
References
Metrics threat_severity

None

 threat_severity

Moderate

Thu, 20 Mar 2025 19:15:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Thu, 20 Mar 2025 10:15:00 +0000

Type Values Removed Values Added
Description A vulnerability in langchain-core versions >=0.1.17,<0.1.53, >=0.2.0,<0.2.43, and >=0.3.0,<0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability to create langchain_core.prompts.ImagePromptTemplate's (and by extension langchain_core.prompts.ChatPromptTemplate's) with input variables that can read any user-specified path from the server file system. If the outputs of these prompt templates are exposed to the user, either directly or through downstream model outputs, it can lead to the exposure of sensitive information.
Title Exposure of Sensitive System Information via ImagePromptTemplate in langchain-ai/langchain
Weaknesses CWE-497
References
Metrics cvssV3_0

{'score': 5.3, 'vector': 'CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N'}

Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: @huntr_ai

Published:

Updated: 2025-03-20T19:02:58.871Z

Reserved: 2024-11-06T19:50:09.607Z

Link: CVE-2024-10940

cve-icon Vulnrichment

Updated: 2025-03-20T17:54:58.847Z

cve-icon NVD

Status : Received

Published: 2025-03-20T10:15:21.850

Modified: 2025-03-20T10:15:21.850

Link: CVE-2024-10940

cve-icon Redhat

Severity : Moderate

Publid Date: 2025-03-20T10:08:48Z

Links: CVE-2024-10940 - Bugzilla

cve-icon OpenCVE Enrichment

Updated: 2025-07-12T22:45:02Z

Weaknesses