CVE-2026-34070
Published:March 31, 2026
Updated:April 23, 2026
LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.
Affected Packages
langchain-core (CONDA):
Affected version(s) >=0.0.10 <1.2.22Fix Suggestion:
Update to version 1.2.22https://github.com/langchain-ai/langchain.git (GITHUB):
Affected version(s) >=langchain-core==0.1.47 <langchain-core==1.2.22Fix Suggestion:
Update to version langchain-core==1.2.22langchain-core (PYTHON):
Affected version(s) >=0.0.1 <1.2.22Fix Suggestion:
Update to version 1.2.22Related Resources (7)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.7
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
NONE
Vulnerable System Availability
NONE
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
7.5
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
NONE
Availability
NONE
Weakness Type (CWE)
Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
EPSS
Base Score:
0.03
