CVE-2025-67510 MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
Prompt injection in Neuron AI framework allows attackers to execute destructive SQL queries via the MySQLWriteTool if exposed to untrusted input.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2025-67510?
CVE-2025-67510 is a critical SQL injection vulnerability in neuron-core neuron-ai, published on 10 Dec 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Which versions are affected by CVE-2025-67510?
2 open source packages ship an affected version, including neuron-core/neuron-ai. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
neuron-core/neuron-ai Packagist | All versions | 2.8.12 |
neuron-core/neuron-ai Packagist | All versions | 2.8.12 |
Products include Neuron-Ai Neuron.
How do I fix CVE-2025-67510?
Upgrade neuron-core/neuron-ai to 2.8.12 or later.
Use parameterised queries everywhere and never build SQL by joining strings. Upgrade affected software first; a web application firewall only buys time. More about SQL injection.
Is CVE-2025-67510 being exploited?
There is no known exploitation of CVE-2025-67510 in the wild and no public exploit code.
Other vulnerabilities in neuron-core neuron-ai
Sources
Also known as GHSA-898v-775g-777c.