Langchain SQL Injection vulnerability

langchain (pip)

In Langchain before 0.0.247, prompt injection allows execution of arbitrary code against the SQL service provided by the chain.

Fix it

pip install --upgrade "langchain>=0.0.247"

First seen: 21 Oct 2023
Last update: 21 Oct 2023, 00:30 UTC
Fixed in: langchain 0.0.247
Identifiers: CVE-2023-32785
Source: GitHub advisory
On the menu as: PyPI packages
LLM gateways

Check this repository for exposure to one security incident from pwned.coffee. Report first, change nothing until I say so.

## Langchain SQL Injection vulnerability
Severity: critical. Patch status: patched.
Affected: langchain (pip)
Fixed in: langchain 0.0.247
Ids: CVE-2023-32785

In Langchain before 0.0.247, prompt injection allows execution of arbitrary code against the SQL service provided by the chain.

## Steps
1. This incident involves a provider (ai-gateways). Search config, CI and env templates (.env.example, wrangler.toml, vercel.json, terraform, workflow secrets) for credentials stored there. List each secret by name, where it is used, and how to rotate it. Never print secret values.

## Report
A table: file, product or package, version in use, affected yes/no, exact fix. Then anything a human has to check outside the repo.

If you have the pwned.coffee MCP server (https://pwned.coffee/mcp), call lookup_cve("CVE-2023-32785") for the latest, and check_repo with this repo's lockfiles, Dockerfiles and workflows for a full receipt.
Sources: https://gist.github.com/rharang/9c58d39db8c01db5b7c888e467c0533f https://github.com/advisories/GHSA-8h5w-f6q9-wg35 https://github.com/langchain-ai/langchain/issues/5923#issuecomment-1696053841 https://github.com/pypa/advisory-database/tree/main/vulns/langchain/PYSEC-2026-372.yaml https://nvd.nist.gov/vuln/detail/CVE-2023-32785
https://pwned.coffee/i/langchain-sql-injection-vulnerability-cve-2023-32785

Sources

Wrong fix version, or a source we missed? Send it back to chef@pwned.coffee with the source, and we'll correct it here.

Totalone very hot coffee