High severity · published Oct 26, 2025
CVE-2025-8709
SQL Injection in langchain-ai/langchain
7.3
CVSS
0.2%
EPSS
No
On KEV
Description
A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne, $gt, $lt, $gte, $lte) where direct string concatenation is used without proper parameterization. This allows attackers to inject arbitrary SQL, leading to unauthorized access to all documents, data exfiltration of sensitive fields such as passwords and API keys, and a complete bypass of application-level security filters.
CVSS vector
CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N
Attack vector
Local
Complexity
Low
Privileges
Low
User interaction
None
Confidentiality
High
Integrity
Low
Availability
None
Scope
Changed
Exploitation
Is it being used?
Exploit prediction (EPSS)0.2% · higher than 12% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LA
langchain-ai/langchain · langchain-ai
through latest · source: vendor
Affected product
LA
langchain-ai/langchain
langchain-ai
More from langchain-ai/langchain
7.5
CVE-2025-6985
XXE Vulnerability in langchain-ai/langchain
7.5
CVE-2025-6984
Sensitive Information Disclosure Due to Insecure XML Parsing in langchain-ai/langchain