Graph data manipulation via prompt-injected Cypher queries
Published Oct 29, 2024 · Updated Oct 15, 2025
SQL injection in LangChain.js before 0.3.1 allows attackers to manipulate graph data through prompt injection in GraphCypherQAChain. The class passes model-generated Cypher derived from a user-influenced question to the configured graph query operation without restricting it to read-only statements. Exploitation requires an application to use this chain with attacker-controlled prompts, and resulting data access, modification, deletion, or interruption is bounded by the graph credentials.
Summary
What happened
SQL injection in LangChain.js before 0.3.1 allows attackers to manipulate graph data through prompt injection in GraphCypherQAChain. The class passes model-generated Cypher derived from a user-influenced question to the configured graph query operation without restricting it to read-only statements. Exploitation requires an application to use this chain with attacker-controlled prompts, and resulting data access, modification, deletion, or interruption is bounded by the graph credentials.
The record
- CVE
- CVE-2024-7042
- Published
- Oct 29, 2024
- Updated
- Oct 15, 2025
- Vendor
- LangChain
- Product
- LangChain.js
- Classifications
- CWE-89
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Oct 29, 2024CVE publishedPublication date reported by the CVE source.
- Oct 15, 2025Record 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 <0.3.1
- Affected versionversion=unspecified <0.3.1
What conditions does exploitation require?
What is affected?
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
- GraphCypherQAChain prompt-injection 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