Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-x48g-hm9c-ww42

llama-index-packs-finchat SQL Injection vulnerability

CVSS 10.0 CriticalCriticalEPSS 0.014 · 73rd percentile

Critical, because:

  • CVSS score 10.0: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 29 Jun 2026, 11:50 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
llama-index-packs-finchatPyPI<=0.3.0No fixed version yet
Identifiers
GHSA-x48g-hm9c-ww42 · CVE-2024-12909 · PYSEC-2026-398
Weakness (CWE)
CWE-89
Tags
Published
29 Jun 2026
Updated
1 Jul 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

The llama-index-packs-finchat package, versions up to and including 0.3.0, has a SQL injection flaw in the run_sql_query function of its database agent. An attacker who can supply input to that function can inject arbitrary SQL, which the source says can lead to remote code execution through PostgreSQL's large object functionality. No fixed version is listed; the maintainers have stopped officially supporting the package and moved it to a stale branch.

Written 10 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
10.0 Critical 3.0 CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H CNA (@huntr_ai)
  • CISA KEV Not listed.
  • EPSS 0.014, the 73rd percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

This record came from the full history of the GitHub Advisory Database, published 29 Jun 2026. New records show when each source confirmed them.

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.