Advisory record · GHSA-898v-775g-777c

Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)

CVSS 9.4 CriticalCriticalEPSS 0.0044 · 38th percentile

Critical, because:

  • CVSS score 9.4: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 9 Dec 2025, 17:19 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
neuron-core/neuron-aiPackagist<2.8.122.8.12
Identifiers
GHSA-898v-775g-777c · CVE-2025-67510 · PKSA-v9n6-t7d1-c4nb
Weakness (CWE)
CWE-250 · CWE-284
Published
9 Dec 2025
Updated
11 Dec 2025

Machine-written summary

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

The neuron-core/neuron-ai Packagist package versions before 2.8.12 are affected. The MySQLWriteTool runs caller-supplied SQL without restriction, so when an agent with this tool is exposed to untrusted input, prompt injection can lead to destructive statements such as DROP TABLE or privilege changes, limited by the database user's permissions. Upgrade to 2.8.12 or later. Until then, do not enable the tool for untrusted agents, and run it with a least-privilege database user.

Written 3 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
9.4 Critical 3.1 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H CNA (GitHub_M)
  • CISA KEV Not listed.
  • EPSS 0.0044, the 38th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

  1. 31 Oct 2026, 14:26 UTC First seen by agentprime
  2. 31 Oct 2026, 14:26 UTC Confirmed by OSV

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.