What’s Vulnerable › Vulnerabilities

CVE-2025-67644: LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method

• Severity: high (CVSS 7.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 2.3% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2025-12-11 · updated 2026-10-08
• Weakness: CWE-89

Description

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.

Affected products

• langchain-ai langgraph-checkpoint-sqlite: before 3.0.1 — fixed in 3.0.1

How to fix

Upgrade to a fixed version: langchain-ai langgraph-checkpoint-sqlite 3.0.1. Check the vendor advisory for mitigations.

References

• https://github.com/langchain-ai/langgraph/commit/297242913f8ad2143ee3e2f72e67db0911d48e2a
• https://github.com/langchain-ai/langgraph/security/advisories/GHSA-9rwj-6rc7-p77c

Get alerted when CVE-2025-67644 or the next vulnerability affects your stack