Browse / AI Framework and Platform Flaws / CVE-2025-8709
LangGraph's SQLite store implementation has a SQL Injection Vulnerability
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- SQL and query injection
- Also involves
- Sensitive Data Disclosure
- Affected
- langgraph-checkpoint-sqlite (PyPI)
- CVSS
- CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N
- EPSS
- 0.2% chance of exploitation in 30 days
How it works, in short
Filter operator handling concatenates input into SQL in the SQLite checkpoint store, so crafted filters can read other records and stored secrets. (Our summary, written by a model. The source text is below.)
Details
A SQL injection vulnerability exists in the langchain-ai/langgraph 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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2025-8709
- https://github.com/langchain-ai/langgraph/pull/5666
- https://github.com/langchain-ai/langgraph/commit/bc9d45b476101e441cb1cc602dea03eb29232de4
- https://github.com/langchain-ai/langgraph
- https://github.com/langchain-ai/langgraph/releases/tag/checkpointsqlite%3D%3D2.0.11
- https://huntr.com/bounties/9793f4b3-76f8-44a4-989f-49a2177ee118
Source: GitHub Advisory Database, used under CC BY 4.0.