CVE-2025-67510 json
MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
published 2025-12-09 11 mo ago modified 2026-09-25 44 d ago also GHSA-898v-775g-777c , EUVD-2025-202170
- cvss
- 9.4
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 35%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- packagist neuron-core/neuron-ai 2.8.12
- neuron-ai neuron 2.8.12
CISA SSVC
- Exploitation
- none
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 10 mo ago
Exploit prediction
0.41% chance of exploitation in the next 30 days, higher than 35% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 9.4 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H |
| GitHub | 3.1 | 9.4 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| packagist | neuron-core/neuron-ai | <2.8.12 |
2.8.12 |
Affected products
- neuron-core neuron-ai
Classification
References
-
github.com
/neuron-core/neuron-ai/commit/44bab85d92bf162898ee48d0bcef6ba0d29b59c9
web, patch
-
github.com
/neuron-core/neuron-ai/security/advisories/GHSA-898v-775g-777c
web, mitigation, vendor-advisory
-
github.com
/neuron-core/neuron-ai/releases/tag/2.8.12
web, product, release-notes
-
nvd.nist.gov
/vuln/detail/CVE-2025-67510
advisory
-
github.com
/neuron-core/neuron-ai
package
Sources
- CVE List CVE-2025-67510
- GitHub Advisory GHSA-898v-775g-777c
- NVD CVE-2025-67510
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.