LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in versions 0.3.81 and 1.2.5.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-502"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/68xxx/CVE-2025-68664.json"
}{
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "0.3.81"
},
{
"introduced": "1.0.0"
},
{
"fixed": "1.2.5"
}
],
"cpe": "cpe:2.3:a:langchain:langchain_core:*:*:*:*:*:python:*:*",
"source": [
"CPE_RANGE",
"REFERENCES"
]
}