---
title: "CVE-2025-67510: Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)"
url: https://erroneo.us/security/cve/CVE-2025-67510/
description: "CVE-2025-67510 (neuron-core/neuron-ai (Composer (PHP))): Neuron is a PHP framework for creating and orchestrating AI Agents. In versions 2.8.11 and below…"
type: vulnerability-record
section: "Security Digest"
date_published: 2025-12-10
date_modified: 2025-12-11
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2025-67510"
kev: false
cvss: 9.4
epss: 0.00408
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2025-67510: Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)

**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?

- No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 0.4% , percentile 34: FIRST’s model estimates a 0.4% chance of exploitation activity in the next 30 days, higher than 34% of all scored CVEs (low). 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 neuron-core/neuron-ai (Composer (PHP)) <= 2.8.11, fixed in 2.8.12 . Check your lockfile, including transitive dependencies.

## What it is

Neuron is a PHP framework for creating and orchestrating AI Agents. In versions 2.8.11 and below, the 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). Deployments that expose an agent with MySQLWriteTool enabled to untrusted input and/or run the tool with a DB user that has broad privileges are impacted. This issue is fixed in version 2.8.12.

## Affected packages

- Composer (PHP) `neuron-core/neuron-ai` <= 2.8.11 → fixed: 2.8.12

## Affected products (CVE record)

- neuron-core neuron-ai: < 2.8.12

## Severity

- GitHub_M CVSS 3.1: 9.4 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H`
- GitHub CVSS 3.1: 9.4 `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation none , automatable yes , technical impact partial .
- FIRST EPSS (model of 2026-10-21): 0.41% probability of exploitation activity in the next 30 days; percentile 34.

## Sources

- [GitHub Advisory GHSA-898v-775g-777c](https://github.com/advisories/GHSA-898v-775g-777c)
- [CVE.org record CVE-2025-67510](https://www.cve.org/CVERecord?id=CVE-2025-67510)
- [NVD entry CVE-2025-67510](https://nvd.nist.gov/vuln/detail/CVE-2025-67510)
- [github.com](https://github.com/neuron-core/neuron-ai/security/advisories/GHSA-898v-775g-777c)
- [github.com](https://github.com/neuron-core/neuron-ai/commit/44bab85d92bf162898ee48d0bcef6ba0d29b59c9)
- [github.com](https://github.com/neuron-core/neuron-ai/releases/tag/2.8.12)

---
Source page: https://erroneo.us/security/cve/CVE-2025-67510/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt