Browse / Direct Prompt Injection / CVE-2024-8309
Langchain SQL Injection vulnerability
- Class
- Direct Prompt Injection (filed by a model that read the advisory)
- Technique
- SQL and query injection
- Also involves
- Improper Output Handling
- Affected
- langchain-community, langchain (PyPI)
- CVSS
- CVSS:3.0/AV:L/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L
- EPSS
- 13.7% chance of exploitation in 30 days
How it works, in short
Prompt-injected text makes the LLM generate Cypher queries that GraphCypherQAChain runs unchecked, letting attackers read, change or delete graph data. (Our summary, written by a model. The source text is below.)
Details
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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2024-8309
- https://github.com/langchain-ai/langchain/commit/64c317eba05fbac0c6a6fc5aa192bc0d7130972e
- https://github.com/langchain-ai/langchain/commit/c2a3021bb0c5f54649d380b42a0684ca5778c255
- https://github.com/langchain-ai/langchain
- https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2024-115.yaml
- https://huntr.com/bounties/8f4ad910-7fdc-4089-8f0a-b5df5f32e7c5
Source: GitHub Advisory Database, used under CC BY 4.0.