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

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

9.4 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H

EPSS

• CVE-2025-67510: 0.41% estimated exploitation activity in the next 30 days; percentile 35.16 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Impact MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare() + execute() without semantic restrictions. This is consistent with the name (“write tool”), but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause execution of destructive queries such as DROP TABLE, TRUNCATE, DELETE, ALTER, or privilege-related statements (subject to DB permissions). Who is impacted: Deployments that expose an agent with MySQLWriteTool enabled to untrusted input and/or run the tool with a DB user that has broad privileges. Patches Not patched in: 2.8.11 Recommended improvements (even if keeping the tool intentionally powerful): - Provide a safer API that supports only constrained operations (e.g., insertRecord, updateRecord) with allowlisted tables/columns. - Add a policy/allowlist layer (e.g., allow only INSERT/UPDATE on selected tables; forbid DROP/TRUNCATE/ALTER/GRANT). - Add optional review workflow: log +…

Published by the source

9 Dec 2025, 17:19 UTC

Last modified by the source

11 Dec 2025, 15:49 UTC

Source last checked

26 Oct 2026, 14:35 UTC

1. Revision 1 · created · 26 Oct 2026

   Published from ghsa record GHSA-898v-775g-777c

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2025-67510

Advisory: Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
IDs: CVE-2025-67510, GHSA-898v-775g-777c
Record: https://patchnext.com/advisories/cve-2025-67510 (revision 1, source checked 26 Oct 2026, 14:35 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Critical (CVSS 9.4)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: neuron-core/neuron-ai 2.8.12. A vendor fix does not mean a deployment is fixed.

## Affected components
- Packagist neuron-core/neuron-ai: affected <= 2.8.11; fixed in 2.8.12

## Suggested inspection (read-only)
- Packagist neuron-core/neuron-ai: check the installed version with your package manager.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on neuron-core/neuron-ai.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-898v-775g-777c (GitHub-reviewed advisory GHSA-898v-775g-777c lists affected ranges: Packagist neuron-core/neuron-ai >=0 <=2.8.11)

Commands are suggestions: review each one before running it.