Cyber Resilience

CVE-2023-38896

Langchain ≤ 0.0.194

Public PoC
Published
15 August 2023
Modified
21 November 2024
Patch / advisory
View advisory
CVSS Score v3.1 9.8
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.015 72th percentile
Risk Priority 74 floored blend · peak EPSS

Summary

CVE-2023-38896 is a critical-severity Injection (CWE-74) vulnerability in Langchain Langchain. Its CVSS base score is 9.8 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 28% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as LLM Application Platforms.

OWASP Top 10 for Web (2025)

A05:2025 Injection

EU & UK References

Vulnerability Data

An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the from_math_prompt and from_colored_object_prompt functions.

CWE(s)
CWE-74

AI Security AnalysisAI

AI Category
LLM Application Platforms
Risk Domain
N/A
OWASP Top 10 for LLMs 2025
None mapped
AI-specific weaknesses CR
CWE-1426CWE-1427
  • CWE-1426 — Untrusted input to prompt fns; LLM output reaches code-exec sink without validation.
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

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.
attack.mitre.org →
T1221 Template Injection Stealth
Adversaries may create or modify references in user document templates to conceal malicious code or force authentication attempts.
attack.mitre.org →
T1659 Content Injection Initial Access
Adversaries may gain access and continuously communicate with victims by injecting malicious content into systems through online network traffic.
attack.mitre.org →
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,…
attack.mitre.org →
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
attack.mitre.org →
T1059.001 PowerShell Execution
Adversaries may abuse PowerShell commands and scripts for execution.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2023-39659Same product: Langchain Langchain
CVE-2023-36188Same product: Langchain Langchain
CVE-2023-32786Same product: Langchain Langchain
CVE-2023-29374Same product: Langchain Langchain
CVE-2024-8309Same product: Langchain Langchain
CVE-2026-25750Same vendor: Langchain
CVE-2024-36420Shared CWE-74
CVE-2023-39661Shared CWE-74
CVE-2023-23749Shared CWE-74
CVE-2023-48835Shared CWE-74

Affected Assets

langchain
langchain
≤ 0.0.194

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

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

SA-11 Developer Testing and Evaluation
addresses: CWE-74

Developer assessments and testing (including injection-focused techniques) identify improper neutralization of special elements, and the verifiable flaw remediation corrects them pre-deployment.

SI-4 System Monitoring
addresses: CWE-74

Identifies indicators of injection attacks (command, SQL, LDAP, etc.) via anomaly and attack monitoring.

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.

A.8.29 Security testing in development and acceptance mostly match
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.

A.8.16 Monitoring activities partial match
finds

Monitoring activities can identify active injection attacks after they occur.

A.8.25 Secure development life cycle partial match
prevents

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

A.8.26 Application security requirements partial match
prevents

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

A.8.27 Secure system architecture and engineering principles partial match
prevents

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

References