Prompt Injection in langchain-ai/langchainjs Leading to SQL Injection
cve-program · CVE-2024-7042
PublishedA 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.
Read the publisher's advisoryeuvd · EUVD-2024-0088
PublishedA 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.
Read the publisher's advisorynvd · CVE-2024-7042
PublishedA 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.
Read the publisher's advisoryosv · GHSA-6m59-8fmv-m5f9
PublishedA 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.
Read the publisher's advisoryAffected versions, risk and source history
Related advisories and sources
Publishers link these advisories through the identifiers shown below. A shared identifier or date alone does not tell you whether your software is affected or whether the advisories describe the same cause.
CVE-2024-7042 · CVE overview and exploitation status
cve-program · CVE-2024-7042
- https://huntr.com/bounties/b612defb-1104-4fff-9fef-001ab07c7b2d
- https://github.com/langchain-ai/langchainjs/commit/615b9d9ab30a2d23a2f95fb8d7acfdf4b41ad7a6
euvd · EUVD-2024-0088
- https://huntr.com/bounties/b612defb-1104-4fff-9fef-001ab07c7b2d
- https://github.com/langchain-ai/langchainjs/commit/615b9d9ab30a2d23a2f95fb8d7acfdf4b41ad7a6
nvd · CVE-2024-7042
- https://github.com/langchain-ai/langchainjs/commit/615b9d9ab30a2d23a2f95fb8d7acfdf4b41ad7a6
- https://huntr.com/bounties/b612defb-1104-4fff-9fef-001ab07c7b2d
osv · GHSA-6m59-8fmv-m5f9
- https://nvd.nist.gov/vuln/detail/CVE-2024-7042
- https://github.com/langchain-ai/langchainjs/commit/615b9d9ab30a2d23a2f95fb8d7acfdf4b41ad7a6
- https://github.com/langchain-ai/langchainjs
- https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2024-114.yaml
- https://huntr.com/bounties/b612defb-1104-4fff-9fef-001ab07c7b2d
Related changes
Linked by CVE identifierNo related changes are available here.