@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.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Privileges Required
Low
Basic privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
High
Complete data leak
Integrity
None
No data modification
Availability
None
No disruption
CVSS Vector v3.1
Weakness Type (CWE)
References 4
https://github.com/langchain-ai/langgraphjs/commit/814c76dc3938d0f6f7e17ca3bc11…
security-advisories@github.com
https://github.com/langchain-ai/langgraphjs/pull/1943
security-advisories@github.com
https://github.com/langchain-ai/langgraphjs/releases/tag/@langchain/langgraph-c…
security-advisories@github.com
https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-5mx2-w598-…
security-advisories@github.com