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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-22"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/34xxx/CVE-2026-34070.json"
}{
"cpe": "cpe:2.3:a:langchain:langchain_core:*:*:*:*:*:python:*:*",
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "1.2.22"
}
],
"source": [
"CPE_RANGE",
"REFERENCES"
]
}