CVE-2025-8709 SQL Injection in langchain-ai/langchain
Attackers can inject SQL via filter operators in LangGraph's SQLite store to exfiltrate sensitive data and bypass security filters.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2025-8709?
CVE-2025-8709 is a high-severity SQL injection vulnerability in langchain-ai/langchain, published on 26 Oct 2025. It can only be exploited from the same machine or local network, with no action from the victim.
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.
Weakness: CWE-89
Which versions are affected by CVE-2025-8709?
3 open source packages ship an affected version, including langgraph-checkpoint-sqlite.
| Package | Affected | Fixed in |
|---|---|---|
langgraph-checkpoint-sqlite PyPI | All versions | 2.0.11 |
langgraph-checkpoint-sqlite PyPI | All versions | 2.0.11 |
langgraph-checkpoint-sqlite PyPI | All versions | 2.0.11 |
How do I fix CVE-2025-8709?
Upgrade langgraph-checkpoint-sqlite to 2.0.11 or later.
Use parameterised queries everywhere and never build SQL by joining strings. Upgrade affected software first; a web application firewall only buys time. More about SQL injection.
Is CVE-2025-8709 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-8709 exists.
Sources
Also known as GHSA-4h97-wpxp-3757, PYSEC-2026-1528.