---
title: "CVE-2024-12909: llama-index-packs-finchat SQL Injection vulnerability"
url: https://erroneo.us/security/cve/CVE-2024-12909/
description: "CVE-2024-12909 (llama-index-packs-finchat (PyPI)): A vulnerability in the FinanceChatLlamaPack of the run-llama/llamaindex repository, versions up to…"
type: vulnerability-record
section: "Security Digest"
date_published: 2025-03-20
date_modified: 2025-04-03
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2024-12909"
kev: false
cvss: 10.0
epss: 0.01444
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2024-12909: llama-index-packs-finchat SQL Injection vulnerability

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 1.4% , percentile 73: FIRST’s model estimates a 1.4% chance of exploitation activity in the next 30 days, higher than 73% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes llama-index-packs-finchat (PyPI) <= 0.3.0, no fixed version listed . Check your lockfile, including transitive dependencies.

## What it is

A vulnerability in the FinanceChatLlamaPack of the run-llama/llamaindex repository, versions up to v0.12.3, allows for SQL injection in the runsqlquery function of the databaseagent. This vulnerability can be exploited by an attacker to inject arbitrary SQL queries, leading to remote code execution (RCE) through the use of PostgreSQL's large object functionality. The issue is fixed in version 0.3.0.

## Affected packages

- PyPI `llama-index-packs-finchat` <= 0.3.0 → fixed: none listed

## Affected products (CVE record)

- run-llama run-llama/llama_index: unspecified < 0.3.0

## Severity

- @huntr_ai CVSS 3.0: 10 `CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`
- GitHub CVSS 3.1: 10.0 `CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 1.44% probability of exploitation activity in the next 30 days; percentile 73.

## Sources

- [GitHub Advisory GHSA-x48g-hm9c-ww42](https://github.com/advisories/GHSA-x48g-hm9c-ww42)
- [CVE.org record CVE-2024-12909](https://www.cve.org/CVERecord?id=CVE-2024-12909)
- [NVD entry CVE-2024-12909](https://nvd.nist.gov/vuln/detail/CVE-2024-12909)
- [huntr.com](https://huntr.com/bounties/44e8177f-200a-4ba3-a12c-8bc21e313a3f)
- [github.com](https://github.com/run-llama/llama_index/commit/5d03c175476452db9b8abcdb7d5767dd7b310a75)
- [github.com](https://github.com/run-llama/llama_index/tree/stale_packages/llama-index-packs/llama-index-packs-finchat)

---
Source page: https://erroneo.us/security/cve/CVE-2024-12909/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt