Vulnerability · Published Oct 26, 2025 · Assigned by @huntr_ai
CVE-2025-8709SQL Injection in langchain-ai/langchain
High 7.3
In plain English
A high-severity SQL injection in langchain-ai/langchain from langchain-ai. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 13% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | langgraph-checkpoint-sqlite | 2.0.11 | GHSA-4h97-wpxp-3757 |
| PyPI | langgraph-checkpoint-sqlite | 2.0.11 | PYSEC-2026-1528 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| langchain-ai | langchain-ai/langchain | unspecified – through latest |
Weakness: CWE-89 · Vector: CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N