Cyber Resilience

CVE-2026-25750

Langchain Langsmith ≤ 0.12.71

Published
04 March 2026
Modified
18 March 2026
Patch / advisory
CVSS Score v4 8.5
Click a component to see what it means
Raw vectorCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS Score 0.0029 22th percentile
Risk Priority 55 floored blend · peak EPSS

Summary

CVE-2026-25750 is a high-severity Injection (CWE-74) vulnerability in Langchain Langsmith. Its CVSS base score is 8.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 22th 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 Privacy and Disclosure risk domain.

The strongest mitigations our analysis identified map to SI-10 (Information Input Validation) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

CVE-2026-25750 is a URL parameter injection vulnerability in LangSmith Studio, part of the Langchain Helm Charts used for deploying Langchain applications on Kubernetes. The issue affects versions prior to langchain-ai/helm 0.12.71 and impacts both LangSmith Cloud and self-hosted deployments. It has a CVSS v3.1 base score of 8.1 (AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N) and is associated with CWE-74 (Improper Neutralization of Special Elements used in an SQL Command).

The vulnerability enables exploitation through social engineering, where an attacker crafts a malicious link that an authenticated LangSmith user clicks, such as via phishing emails or chat applications. This action transmits the victim's bearer token, user ID, and workspace ID to an attacker-controlled server. With the stolen token, the attacker can impersonate the user, accessing any LangSmith resources or performing actions authorized within the victim's workspace. Tokens expire after 5 minutes, but repeated attacks are feasible if the user can be tricked into clicking additional links.

According to the advisory at https://github.com/langchain-ai/helm/security/advisories/GHSA-r8wq-jwgw-p74g, version 0.12.71 resolves the issue by adding validation that requires user-defined allowed origins for the baseUrl parameter, blocking token transmission to unauthorized servers. No workarounds exist, and self-hosted deployments must upgrade to the patched version.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

Langchain Helm Charts are Helm charts for deploying Langchain applications on Kubernetes. Prior to langchain-ai/helm version 0.12.71, a URL parameter injection vulnerability existed in LangSmith Studio that could allow unauthorized access to user accounts through stolen authentication tokens. The vulnerability…

more

affected both LangSmith Cloud and self-hosted deployments. Authenticated LangSmith users who clicked on a specially crafted malicious link would have their bearer token, user ID, and workspace ID transmitted to an attacker-controlled server. With this stolen token, an attacker could impersonate the victim and access any LangSmith resources or perform any actions the user was authorized to perform within their workspace. The attack required social engineering (phishing, malicious links in emails or chat applications) to convince users to click the crafted URL. The stolen tokens expired after 5 minutes, though repeated attacks against the same user were possible if they could be convinced to click malicious links multiple times. The fix in version 0.12.71 implements validation requiring user-defined allowed origins for the baseUrl parameter, preventing tokens from being sent to unauthorized servers. No known workarounds are available. Self-hosted customers must upgrade to the patched version.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Privacy and Disclosure
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: ai, langchain

Related Threats

MITRE ATT&CK Enterprise Techniques

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1221 Template Injection Stealth
Adversaries may create or modify references in user document templates to conceal malicious code or force authentication attempts.
T1659 Content Injection Initial Access
Adversaries may gain access and continuously communicate with victims by injecting malicious content into systems through online network traffic.
T1674 Input Injection Execution
Adversaries may simulate keystrokes on a victim’s computer by various means to perform any type of action on behalf of the user, such as launching the command interpreter using keyboard shortcuts, typing an inline script to be executed,…
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
T1059.001 PowerShell Execution
Adversaries may abuse PowerShell commands and scripts for execution.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2023-39659Same vendor: Langchain
CVE-2023-36188Same vendor: Langchain
CVE-2023-38896Same vendor: Langchain
CVE-2023-32786Same vendor: Langchain
CVE-2023-29374Same vendor: Langchain
CVE-2024-8309Same vendor: Langchain
CVE-2026-22744Shared CWE-74
CVE-2023-23749Shared CWE-74
CVE-2023-48835Shared CWE-74
CVE-2023-51939Shared CWE-74

Affected Assets

langchain
langsmith
≤ 0.12.71

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)

Validate
Prove the fix (OWASP ASVS)
  • V1.2.1
  • V1.2.3
  • V1.2.5
  • V1.2.8

Mitigating Controls (NIST 800-53 r5) AI

SI-10 directly requires validation of information inputs to reject malformed or special-element content before it reaches downstream parsers.

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.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly require input validation and output encoding that prevent injection flaws.

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.

finds

Security testing in development catches injection vulnerabilities before release.

A.8.15 Logging partial match
finds

Logging supports detection of injection attempts but does not prevent the weakness.

finds

Monitoring activities can identify active injection attacks after they occur.

prevents

Secure development life cycle mandates input validation and output encoding that directly prevent injection flaws.

prevents

Application security requirements explicitly call for controls against injection attacks in software design.

prevents

Secure architecture principles reduce injection surfaces but do not prescribe specific neutralization techniques.

References