CVE-2024-8309

SQL Injection in langchain-ai/langchain

A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in multi-tenant security environments, and data integrity issues. Attackers can create, update, or delete nodes and relationships without proper authorization, extract sensitive data, disrupt services, access data across different tenants, and compromise the integrity of the database.

Affected

langchain-ai · langchain-ai/langchain

CVSS v4.0 GitHub

2.1 LOWCVSS:4.0/AV:L/AC:L/AT:P/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N

CVSS v3.1 NVD

9.8 CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS v3.0 HUNTR

4.9 MEDIUMCVSS:3.0/AV:L/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L

EPSS

13.74% chance of exploitation in the next 30 days, 96th percentile

Published

2024-10-29

Updated

2025-10-15

Proof-of-concept exploits (1)

• liadlevy/CVE-2024-83093★ · 2024-10-05

Security advisories

• https://huntr.com/bounties/8f4ad910-7fdc-4089-8f0a-b5df5f32e7c5
• advisories/GHSA-45pg-36p6-83v9
• langchain-ai/langchain/commit/c2a3021bb0c5f54649d380b42a0684ca5778c255

References

• CVE Record
• NVD entry