CVE-2025-67644: high-severity vulnerability in langchain-ai langgraph
LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
21Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 7.3epss 2.3%
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.
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N
Affected products
langchain-ai · langgraphRelated CVEs — langchain-ai langgraph
In the same product, most dangerous first.
CVE-2026-28277MEDIUMLangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loadingEPSS 5.5%CVE-2025-64439HIGHLangGraph Checkpoint affected by RCE in "json" mode of JsonPlusSerializerEPSS 0.9%CVE-2026-118667MEDIUMLangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requestsEPSS 0.4%CVE-2026-71433MEDIUMLangGraph: Namespace prefix matching crosses segment boundaries in Postgres and SQLite storesEPSS 0.4%CVE-2026-115883MEDIUMLangGraph: Namespace labels containing `.` reach other namespaces in Postgres and SQLite storesEPSS 0.3%CVE-2026-104873HIGHLangGraph SDK custom auth silently ignores actions= on resource decoratorsEPSS 0.3%