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

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• 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.

From the GitHub advisory

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

Weakness type: CWE-250, CWE-284.

Product: neuron-core/neuron-ai (Composer (PHP)) · Assigned by: GitHub_M · Published: 2025-12-10

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Privileges required: none (no login)
• User interaction: none
• Scope: unchanged

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• 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.

Timeline

• 2025-12-09 — GitHub-reviewed advisory GHSA-898v-775g-777c published (critical)
• 2025-12-10 — CVE record published by GitHub_M
• 2025-12-11 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-898v-775g-777c github.com
2. CVE.org record CVE-2025-67510 cve.org
3. NVD entry CVE-2025-67510 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. github.com github.com

Critical Composer (PHP) advisories · Today’s Security Digest