CVE-2025-67644 json
LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method
published 2025-12-10 10 mo ago modified 2026-10-08 32 d ago also GHSA-9rwj-6rc7-p77c , PYSEC-2026-1530 , EUVD-2025-202333
- cvss
- 7.3
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 2.3%
- EPSS 2.3% chance of exploitation in 30 days, percentile 83%
- 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). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by interpolating filter keys directly into f-strings without validation. This issue is fixed in version 3.0.1.
Patch / fix
- pypi langgraph-checkpoint-sqlite 3.0.1
- langchain langgraph-checkpoint-sqlite 3.0.1
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
- Assessed
- 10 mo ago
Exploit prediction
2.31% chance of exploitation in the next 30 days, higher than 83% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/langchain-ai/langgraph/security/advisories/GHSA-9rwj-6rc7-p77c 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 |
| NVD | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| 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 | <3.0.1 |
3.0.1 |
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/297242913f8ad2143ee3e2f72e67db0911d48e2a
web, patch
-
github.com
/langchain-ai/langgraph/security/advisories/GHSA-9rwj-6rc7-p77c
web, exploit, vendor-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2025-67644
advisory
-
github.com
/langchain-ai/langgraph
package
-
pypi.org
/project/langgraph-checkpoint-sqlite
package
-
github.com
/advisories/GHSA-9rwj-6rc7-p77c
advisory
Sources
- CVE List CVE-2025-67644
- GitHub Advisory GHSA-9rwj-6rc7-p77c
- NVD CVE-2025-67644
- OSV PYSEC-2026-1530
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.