9.4

CVSS Score

3.1

-

CVSS Score

Basic Information

Concerned about an active attack path?

Talk to our security experts and see Miggo in action.

Miggo Vulnerability Database

→

CVE-2025-67510

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

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.

(GitHub Advisory)

Miggo Vulnerability Database

→

CVE-2025-67510

CVE-2025-67510:

9.4

CVSS Score

3.1

-

CVSS Score

Basic Information

Is this CVE running in your environment?

Easily map the attack path and prioritize which CVEs are a threat to your organization

Validate Exposure

Technical Details

Package Name	Ecosystem	Vulnerable Versions	First Patched Version
neuron-core/neuron-ai	composer	<= 2.8.11	2.8.12

Technical Details

Vulnerability Intelligence
Miggo AI

Root Cause Analysis

The vulnerability described is an arbitrary SQL execution in the MySQLWriteTool component of the neuron-core/neuron-ai package. The analysis began by identifying the vulnerable and patched versions, which are <= 2.8.11 and 2.8.12 respectively. By comparing the git tags for these versions, a set of commits related to the patch was identified.

The core of the vulnerability lies in the __invoke method of the MySQLWriteTool class, which is responsible for executing the provided SQL query. The security patches revolve around the introduction and enhancement of a validate method, which is called by __invoke to check the query against a list of forbidden, high-risk SQL statements.

Commit 74a19aa0a94cbe982cf28fb1452d45ddca7a76c1 modifies the __invoke function, confirming that it calls the validate function. This makes __invoke a key function in the exploitation process, as it's the entry point for the malicious query.

Commit 44bab85d92bf162898ee48d0bcef6ba0d29b59c9 modifies the validate function itself. This function contains the security logic to deny dangerous queries. Therefore, any attempt to exploit this vulnerability would involve this function being called.

Both __invoke and validate from the Neuron\Tools\Toolkits\MySQL\MySQLWriteTool class are therefore identified as the vulnerable functions that would appear in a runtime profile during an exploitation attempt.

Vulnerable functions

Only Mi**o us*rs **n s** t*is s**tion

Vulnerability Intelligence
Miggo AI

Unlock WAF rules for this CVE

Generate vendor-ready rules for the observed attack patterns, plus reasoning and safe deployment guidance

Get WAF rules

WAF Protection Rules

WAF Rule

W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.W** rul*s *v*il**l* *or Mi**o *ustom*rs only.

Reasoning

*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.*v*il**l* *or Mi**o *ustom*rs only.