Medium severity · published Feb 20, 2026
CVE-2026-27022
RediSearch Query Injection in @langchain/langgraph-checkpoint-redis
6.5
CVSS
4%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
Attack vector
Network
Complexity
Low
Privileges
Low
User interaction
None
Confidentiality
High
Integrity
None
Availability
None
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)4.0% · higher than 90% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LA
langgraphjs · langchain-ai
< 1.0.2 · source: vendor
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-27022
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-27022
github.com
https://github.com/langchain-ai/langgraphjs/commit/814c76dc3938d0f6f7e17ca3bc11d6a12270b2a1
github.com
https://github.com/langchain-ai/langgraphjs/pull/1943
github.com
https://github.com/langchain-ai/langgraphjs/releases/tag/@langchain/langgraph-checkpoint-redis@1.0.2
github.com
https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-5mx2-w598-339m
More from langgraphjs
6.7
CVE-2026-48121
@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access
