by Kastro
Paper/Archive/CVE-2024-7042

CVE-2024-7042

langchain-ai langchain-ai/langchainjs — Prompt Injection in langchain-ai/langchainjs Leading to SQL Injection

EPSS 0.3%public exploitCVSS 9.8
critical.is priorityof 100
44
CVSS 9.8 (NVD)9.8 / 10 × 3029.4Not in CISA KEV+300.0EPSS percentile 24.0.240 × 204.8Exploit: SSVC poc+1010.0SSVC exploitation: poc+100.0
Description · from the CVE record

A vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits 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

ProductAffectedFixed inSource
langchain-ai/langchainjsunspecified – < 0.3.10.3.1CNA
langchainjs< 0.3.10.3.1CISA-ADP

Scores by source

NVD9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
@huntr_ai (CNA)4.9CVSS:3.0/AV:L/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L
CISA ADPSSVCExploitation: poc · Automatable: no · Technical impact: partial

References

refhuntr.com/bounties/b612defb-1104-4fff-9fef-001ab07c7b2drefgithub.com/langchain-ai/langchainjs/commit/615b9d9ab30a2d23a2f95fb8d7acfdf4b41ad7a6