Intel

AIKIDO-2026-10787

neo4j-graphrag is vulnerable to Improper Input Validation

Improper Input Validation Pre-CVE
Found by Aikido Intel before public disclosure or CVE publication.
Published May 8, 2026

65

Medium Risk

This Affects:

PYTHONneo4j-graphrag
0.0.1 - 1.15.0
Fixed in 1.16.0
Are you affected? Scan for Free

TL;DR

Text2CypherRetriever previously executed LLM-generated Cypher directly, which could be coerced via prompt injection into destructive/write queries (e.g., DETACH DELETE). It now runs EXPLAIN first (read-only) to determine the query type and refuses to execute anything not classified as read-only, raising Text2CypherRetrievalError.

Who does this affect?

You are affected if you are using a version that falls within the vulnerable range.

Background info

neo4j-graphrag is vulnerable to Improper Input Validation in versions 0.0.1 - 1.15.0.

How to fix this

Upgrade the neo4j-graphrag library to the patch version.

Are You Affected?

Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.

Free. No credit card required.

Aikido Platform