CVE-2025-67510: Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
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…
Published Dec 9, 2025 · Updated Dec 11, 2025
Affected packages
neuron-core/neuron-ai
- Ecosystem
- Composer (PHP)
- Affected
- <= 2.8.11
- Fixed in
- 2.8.12
- Check
composer show neuron-core/neuron-ai
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
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
Not patched in: 2.8.11
Recommended improvements (even if keeping the tool intentionally powerful):
- Provide a safer API that supports only constrained operations (e.g.,
insertRecord,updateRecord) with allowlisted tables/columns.
- Add a policy/allowlist layer (e.g., allow only
INSERT/UPDATEon selected tables; forbidDROP/TRUNCATE/ALTER/GRANT).
- Add optional review workflow: log + require human approval for high-risk statements; or “dry-run” mode.
- Document strongly that the tool must not be exposed to untrusted prompts without additional safeguards.
Workarounds
- Do not enable
MySQLWriteToolfor public/untrusted agents.
- Use a dedicated DB user with least privilege:
- no
DROP, noALTER, noGRANT, no access to sensitive tables unless necessary
- Add an application-layer policy rejecting high-risk statements (
DROP,TRUNCATE,ALTER,GRANT,REVOKE,CREATE USER, etc.).
- Implement authorization gating for tool calls (RBAC, allow tool use only for trusted operators).
Credited to siewer.
References
- https://github.com/neuron-core/neuron-ai/security/advisories/GHSA-898v-775g-777c
- https://nvd.nist.gov/vuln/detail/CVE-2025-67510
- https://github.com/neuron-core/neuron-ai/commit/44bab85d92bf162898ee48d0bcef6ba0d29b59c9
- https://github.com/neuron-core/neuron-ai/releases/tag/2.8.12
- https://github.com/advisories/GHSA-898v-775g-777c
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
