Graph-data compromise via unvalidated Cypher execution
Published Jul 9, 2026 · Updated Jul 9, 2026
Cypher injection in Langroid before 0.65.5 allows remote attackers to read, alter, or destroy Neo4j graph data through agent prompts. Neo4jChatAgent forwards LLM-generated query text from CypherRetrievalTool and CypherCreationTool directly to session.run and tx.run without validation or a statement-type allowlist. Prompt influence is sufficient for graph compromise; OS-command and filesystem access additionally require APOC or privileged dbms.security procedures on the database role.
Summary
What happened
Cypher injection in Langroid before 0.65.5 allows remote attackers to read, alter, or destroy Neo4j graph data through agent prompts. Neo4jChatAgent forwards LLM-generated query text from CypherRetrievalTool and CypherCreationTool directly to session.run and tx.run without validation or a statement-type allowlist. Prompt influence is sufficient for graph compromise; OS-command and filesystem access additionally require APOC or privileged dbms.security procedures on the database role.
The record
- CVE
- CVE-2026-55615
- Published
- Jul 9, 2026
- Updated
- Jul 9, 2026
- Vendor
- Langroid
- Product
- Langroid
- Classifications
- CWE-74
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 9, 2026CVE publishedPublication date reported by the CVE source.
- Jul 9, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.65.5
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Neo4jChatAgent Cypher execution proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo