Critical severity · published Dec 10, 2025
CVE-2025-67510
MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
9.4
CVSS
0.4%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
Low
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.4% · higher than 35% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
NE
neuron-ai · neuron-core
< 2.8.12 · source: vendor
NE
Neuron · Neuron-ai
before 2.8.12 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-67510
CVE.org
https://www.cve.org/CVERecord?id=CVE-2025-67510
Patch
https://github.com/neuron-core/neuron-ai/commit/44bab85d92bf162898ee48d0bcef6ba0d29b59c9
Product
https://github.com/neuron-core/neuron-ai/releases/tag/2.8.12
Mitigation
https://github.com/neuron-core/neuron-ai/security/advisories/GHSA-898v-775g-777c
More from neuron-ai
8.2
CVE-2025-67509
MySQLSelectTool Read-Only Bypass via SELECT INTO OUTFILE Allows Arbitrary File Write
