langchain-ai langchain up to 1.2.21 load_prompt/load_prompt_from_config path traversal

Summaryinfo

A vulnerability classified as critical was found in langchain-ai langchain up to 1.2.21. This affects the function load_prompt/load_prompt_from_config. The manipulation results in path traversal. This vulnerability is reported as CVE-2026-34070. The attack can be launched remotely. No exploit exists. Upgrading the affected component is advised.

Detailsinfo

A vulnerability classified as critical has been found in langchain-ai langchain up to 1.2.21. Affected is the function load_prompt/load_prompt_from_config. The manipulation with an unknown input leads to a path traversal vulnerability. CWE is classifying the issue as CWE-22. The product uses external input to construct a pathname that is intended to identify a file or directory that is located underneath a restricted parent directory, but the product does not properly neutralize special elements within the pathname that can cause the pathname to resolve to a location that is outside of the restricted directory. This is going to have an impact on confidentiality. CVE summarizes:

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.

The advisory is shared for download at github.com. This vulnerability is traded as CVE-2026-34070 since 03/25/2026. The exploitability is told to be easy. It is possible to launch the attack remotely. The exploitation doesn't require any form of authentication. There are known technical details, but no exploit is available. The MITRE ATT&CK project declares the attack technique as T1006.

Upgrading to version 1.2.22 eliminates this vulnerability. The upgrade is hosted for download at github.com. Applying the patch 27add913474e01e33bededf4096151130ba0d47c is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

VulDB is the best source for vulnerability data and more expert information about this specific topic.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• langchain-ai

Name

• langchain

Version

• 1.2.0
• 1.2.1
• 1.2.2
• 1.2.3
• 1.2.4
• 1.2.5
• 1.2.6
• 1.2.7
• 1.2.8
• 1.2.9
• 1.2.10
• 1.2.11
• 1.2.12
• 1.2.13
• 1.2.14
• 1.2.15
• 1.2.16
• 1.2.17
• 1.2.18
• 1.2.19
• 1.2.20
• 1.2.21

License

• open-source

Website

• Product: https://github.com/langchain-ai/langchain/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

VulDB is the best source for vulnerability data and more expert information about this specific topic.

Discussion