LangChain is a framework for building LLM-powered applications. Prior to 1.1.1, @langchain/redis does not escape attacker-controlled values in structured RediSearch TAG filters and structured RediSearch TEXT filters, allowing injected RediSearch syntax to alter or broaden the generated search query. When an application uses an attacker-influenceable filter as a tenant or document-access boundary, the modified query can expose indexed documents outside the attackers intended scope. This issue is fixed in version 1.1.1.
Weakness
The product generates a query intended to access or manipulate data in a data store such as a database, but it does not neutralize or incorrectly neutralizes special elements that can modify the intended logic of the query.
Extended Description
Depending on the capabilities of the query language, an attacker could inject additional logic into the query to:
The ability to execute additional commands or change which entities are returned has obvious risks. But when the product logic depends on the order or number of entities, this can also lead to vulnerabilities. For example, if the query expects to return only one entity that specifies an administrative user, but an attacker can change which entities are returned, this could cause the logic to return information for a regular user and incorrectly assume that the user has administrative privileges. While this weakness is most commonly associated with SQL injection, there are many other query languages that are also subject to injection attacks, including HTSQL, LDAP, DQL, XQuery, Xpath, and “NoSQL” languages.
Related Attack Patterns
References
- https://github.com/langchain-ai/langchainjs/commit/880e3969ea643a2147777a4d5e8bd606a697edf7
- https://github.com/langchain-ai/langchainjs/pull/10701
- https://github.com/langchain-ai/langchainjs/releases/tag/@langchain/redis@1.1.1
- https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-5x6v-p487-7qh2