Medium severity6.5NVD Advisory· Published Feb 20, 2026· Updated Apr 15, 2026
CVE-2026-27022
CVE-2026-27022
Description
@langchain/langgraph-checkpoint-redis is the Redis checkpoint and store implementation for LangGraph. A query injection vulnerability exists in the @langchain/langgraph-checkpoint-redis package's filter handling. The RedisSaver and ShallowRedisSaver classes construct RediSearch queries by directly interpolating user-provided filter keys and values without proper escaping. RediSearch has special syntax characters that can modify query behavior, and when user-controlled data contains these characters, the query logic can be manipulated to bypass intended access controls. This vulnerability is fixed in 1.0.2.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
@langchain/langgraph-checkpoint-redisnpm | < 1.0.2 | 1.0.2 |
Affected products
2Patches
Vulnerability mechanics
References
6- github.com/advisories/GHSA-5mx2-w598-339mghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-27022ghsaADVISORY
- github.com/langchain-ai/langgraphjs/commit/814c76dc3938d0f6f7e17ca3bc11d6a12270b2a1nvdWEB
- github.com/langchain-ai/langgraphjs/pull/1943nvdWEB
- github.com/langchain-ai/langgraphjs/releases/tag/@langchain/langgraph-checkpoint-redis@1.0.2nvdWEB
- github.com/langchain-ai/langgraphjs/security/advisories/GHSA-5mx2-w598-339mnvdWEB
News mentions
4- 15th June – Threat Intelligence ReportCheck Point Research · Jun 15, 2026
- Critical Vulnerability Chain in LangGraph Allows Attackers to Gain Full Server ControlCyber Security News · Jun 12, 2026
- LangGraph Flaw Chain Exposes Self-Hosted AI Agents to Remote Code ExecutionThe Hacker News · Jun 12, 2026
- From SQLi to RCE – Exploiting LangGraph’s CheckpointerCheck Point Research · Jun 11, 2026