CVE-2026-34070
LangChain Core has Path Traversal vulnerabilites in legacy load_prompt functions
- Published
- Mar 31, 2026
- Updated
- Aug 25, 2026
- Assigning CNA
- GitHub_M
- Evidence observed
- Aug 25, 2026
Primary CVSS
nvd · CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:NLow · next 30 days
- Percentile
- 70.5%
- Model date
- Sep 21, 2026
EPSS is a statistical estimate, not a certainty or a measure of impact. Combine it with CVSS, KEV status, exposure and your environment.
Summary
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.
Sources
1I Found a Zero-Day Vulnerability in langchain — Here’s How It Went
Responsible use
Use vulnerability information only on systems you own or are authorized to test. Kitploit links to public research metadata and does not store exploit code or malicious payloads.