CVE-2026-34070
Last modified
CVE-2026-34070 is a high-severity vulnerability rated 7.5/10 on the CVSS scale. 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. EPSS estimates a 1.07% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Langchain | Langchain Core | < 1.2.22 |
References
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54Exploit, Vendor Advisory
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54Exploit, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-34070?
How severe is CVE-2026-34070?
How do I fix CVE-2026-34070?
Are you affected by CVE-2026-34070?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
