PT-2024-38042 · Langchain Ai · Langchainjs

Published 2024-10-29 · Updated 2024-10-31 · CVE-2024-7042

Positive Technologies (AI Summary)

CVSS v3.1

9.8

Critical

Base vector

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

Name of the Vulnerable Software and Affected Versions langchain-ai/langchainjs versions 0.2.5 and later

Description The issue allows for prompt injection, leading to SQL injection, which can result in 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.

Recommendations For langchain-ai/langchainjs version 0.2.5, consider disabling the GraphCypherQAChain class until a patch is available to prevent prompt injection and subsequent SQL injection attacks. At the moment, there is no information about a newer version that contains a fix for this vulnerability.

Exploit

SQL injection

Weakness Enumeration

CWE-89

Related Identifiers

CVE-2024-7042

GHSA-6M59-8FMV-M5F9

PYSEC-2024-114

Affected Products

Langchainjs

References · 9

• 🔥 https://huntr.com/bounties/b612defb-1104-4fff-9fef-001ab07c7b2d · Exploit
• https://github.com/langchain-ai/langchainjs/commit/615b9d9ab30a2d23a2f95fb8d7acfdf4b41ad7a6 · Patch
• https://osv.dev/vulnerability/PYSEC-2024-114 · Vendor Advisory
• https://nvd.nist.gov/vuln/detail/CVE-2024-7042 · Security Note
• https://osv.dev/vulnerability/CVE-2024-7042 · Vendor Advisory
• https://osv.dev/vulnerability/GHSA-6m59-8fmv-m5f9 · Vendor Advisory
• https://github.com/langchain-ai/langchainjs · Note
• https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2024-114.yaml · Note
• https://t.me/cvedetector/9322 · Telegram Post