7.5
High
CVE-2026-34070 LangChain is a framework for building agents and LLM-powered applications
Description
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 products and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| langchain 1.2 | earliest → < 1.2.22 | 1.2.22 |
| Red Hat Ansible Automation Platform 2.5 1787229385 | earliest → < 1787229385 | 1787229385 |
| Red Hat Ansible Automation Platform 2.5 1780082949 | earliest → < 1780082949 | 1780082949 |
| OpenShift Lightspeed | Versions not published | |
| Red Hat Ansible Automation Platform 2 | Versions not published | |
| Red Hat OpenShift AI (RHOAI) | Versions not published | |
| Red Hat OpenShift AI 3.3 1782471606 | earliest → < 1782471606 | 1782471606 |
References
- github.com github.com
- github.com github.com
- github.com github.com
Timeline
- Published
- Last modified
Other CVEs of langchain
The 9 CVEs of langchain →
CVE-2026-55443
LangChain is a framework for building agents and LLM-powered applications
5.1
Medium
CVE-2026-44843
LangChain is a framework for building agents and LLM-powered applications
8.2
High
CVE-2026-40087
LangChain is a framework for building agents and LLM-powered applications
5.3
Medium
CVE-2026-26013
LangChain is a framework for building agents and LLM-powered applications
3.7
Low