UTC
High

LangGraph's SQLite is vulnerable to SQL injection via metadata filter key in SQLite checkpointer list method

CVE-2025-67644 · GHSA-9rwj-6rc7-p77c · published 2025-12-10 · updated 2025-12-24

Severity
High
CVSS score
7.3
Chance of exploitation (EPSS)
2.5%
Fixed in
3.0.1
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

Attackers who control metadata filter keys can execute arbitrary sql queries against the database.

What to do

Upgrade langgraph-checkpoint-sqlite to 3.0.1 or later.

for querykey, queryvalue in metadata_filter.items():

Affected
PackageRegistryAffectedFixed in
langgraph-checkpoint-sqlitePyPI< 3.0.13.0.1
Also in langgraph-checkpoint-sqlite
  1. HighLangGraph SQLite Checkpoint Filter Key SQL Injection POC for SqliteStorelanggraph-checkpoint-sqlite
  2. HighLangGraph's SQLite store implementation has a SQL Injection Vulnerabilitylanggraph-checkpoint-sqlite
  3. MediumLangGraph: Namespace labels containing `.` reach other namespaces in Postgres and SQLite storeslanggraph-checkpoint-postgres, langgraph-checkpoint-sqlite
  4. MediumLangGraph: Namespace prefix matching crosses segment boundaries in Postgres and SQLite storeslanggraph-checkpoint-postgres, langgraph-checkpoint-sqlite

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].