CVE-2025-64104 json
LangGraph SQLite Checkpoint Filter Key SQL Injection POC for SqliteStore
published 2025-10-29 12 mo ago modified 2026-10-28 11 d ago also EUVD-2025-36720 , GHSA-7p73-8jqx-23r8 , PYSEC-2026-1529
- cvss
- 7.3
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.2%
- EPSS 0.2% chance of exploitation in 30 days, percentile 15%
- public exploits
- 0
- none known
Summary
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Prior to 2.0.11, LangGraph's SQLite store implementation contains SQL injection vulnerabilities using direct string concatenation without proper parameterization, allowing attackers to inject arbitrary SQL and bypass access controls. This vulnerability is fixed in 2.0.11.
Patch / fix
- pypi langgraph-checkpoint-sqlite 2.0.11
- langchain-ai langgraph-checkpoint-sqlite 2.0.11
- langchain langgraph-checkpoint-sqlite 2.0.11
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- 12 mo ago
Exploit prediction
0.24% chance of exploitation in the next 30 days, higher than 15% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/langchain-ai/langgraph/security/advisories/GHSA-7p73-8jqx-23r8 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 7.3 | CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N |
| GitHub | 3.1 | 7.3 | CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N |
| OSV | 3.1 | 7.3 | CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | langgraph-checkpoint-sqlite | <2.0.11 |
2.0.11 |
Affected products
- langchain-ai langgraph
Classification
- Weakness
-
- CWE-89 Improper Neutralization of Special Elements used in an SQL Command
References
-
github.com
/langchain-ai/langgraph/commit/bc9d45b476101e441cb1cc602dea03eb29232de4
web
-
github.com
/langchain-ai/langgraph/security/advisories/GHSA-7p73-8jqx-23r8
exploit, web
-
nvd.nist.gov
/vuln/detail/CVE-2025-64104
advisory
-
github.com
/langchain-ai/langgraph
package
-
github.com
/pypa/advisory-database/tree/main/vulns/langgraph-checkpoint-sqlite/PYSEC-2026-1529.yaml
web
-
pypi.org
/project/langgraph-checkpoint-sqlite
package
-
github.com
/advisories/GHSA-7p73-8jqx-23r8
advisory
Sources
- CVE List CVE-2025-64104
- GitHub Advisory GHSA-7p73-8jqx-23r8
- NVD CVE-2025-64104
- OSV PYSEC-2026-1529
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.