CriticalVulnerabilityLLM-specific

CVE-2024-7042: langchainjs GraphCypherQAChain prompt injection leading to SQL injection

Source: NVD(opens in a new tab)
Identifier: CVE-2024-7042
Published: October 29, 2024
Record updated: October 9, 2026

Affected: @langchain/community < 0.3.3
Fixed in: 0.3.3
released September 25, 2024, 34 days before disclosure
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.3%

Summary

CVE-2024-7042 affects the GraphCypherQAChain class in langchain-ai/langchainjs, in version 0.2.5 and all versions containing this class. Prompt injection in the class leads to SQL injection, allowing an attacker to create, update, or delete nodes and relationships without authorization, extract sensitive data, and cause denial of service by deleting all data. The flaw also enables access across tenants in multi-tenant environments and damages database integrity.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 9.8(critical)
Patch available: Yes
EPSS: 0.3%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-89
Attack pattern (CAPEC): CAPEC-66
AI threat technique (MITRE ATLAS): AML.T0051

Affected

Packages: @langchain/community@< 0.3.3 (fixed: 0.3.3)
Vendors: LangChain

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Trivial
AI component targeted: Framework
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2024-7042

First tracked: February 15, 2026 at 08:35 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

@langchain/communitynpmLLM dependency since 2023-12-08 · 4 tracked dependents

Summary

Mitigation

Affected packages in the Exposure Registry

Related items