CVE-2026-34070 - LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions
CVE ID :CVE-2026-34070
Published : March 31, 2026, 3:15 a.m. | 3 hours, 50 minutes ago
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.
Severity: 7.5 | HIGH
Visit the link for more details, such as CVSS details, affected products, timeline, and more...
Published : March 31, 2026, 3:15 a.m. | 3 hours, 50 minutes ago
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.
Severity: 7.5 | HIGH
Visit the link for more details, such as CVSS details, affected products, timeline, and more...