CVE-2026-105799 LangChain: RediSearch Filter Injection via Unescaped Tag/Text Values
Attackers can inject RediSearch syntax to bypass access controls and read unauthorized indexed documents in LangChain Redis integrations.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-105799?
CVE-2026-105799 is a low-severity vulnerability in @langchain langchainjs, published on 6 Oct 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
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 attacker's intended scope. This issue is fixed in version 1.1.1.
Weakness: CWE-943
Which versions are affected by CVE-2026-105799?
2 open source packages ship an affected version, including @langchain/redis.
| Package | Affected | Fixed in |
|---|---|---|
@langchain/redis npm | All versions | 1.1.1 |
@langchain/redis npm | All versions | 1.1.1 |
How do I fix CVE-2026-105799?
Upgrade @langchain/redis to 1.1.1 or later.
Is CVE-2026-105799 being exploited?
There is no known exploitation of CVE-2026-105799 in the wild and no public exploit code.
Sources
Also known as CLEANSTART-2026-TL42570, GHSA-5x6v-p487-7qh2.