Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
Published 9 Dec 2025 · Updated 11 Dec 2025
Is your project on an affected neuron-core/neuron-ai?
Look after several Laravel or PHP apps? Indie watches up to 15 repos, private ones too, for $5 a month. See Indie
Affected package
- Affected
- <2.8.12
- Fixed in
- 2.8.12
composer require neuron-core/neuron-ai:^2.8.12Details
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).
Is GHSA-898v-775g-777c in any of your client repos?
Checking one package by hand is fine. Checking it across forty client projects is not. NPMscan reads the lockfiles in every GitHub repo you pick, finds each project with an affected neuron-core/neuron-ai, and gives you the command that fixes it.
More advisories for neuron-core/neuron-ai
- HighCVE-2025-67509Neuron MySQLSelectTool “read-only” bypass via `SELECT ... INTO OUTFILE` (file write → potential RCE) · 9 Dec 2025
References
- Linkgithub.com/neuron-core/neuron-ai/security/advisories/GHSA-898v-775g-777c
- Advisorynvd.nist.gov/vuln/detail/CVE-2025-67510
- Linkgithub.com/neuron-core/neuron-ai/commit/44bab85d92bf162898ee48d0bcef6ba0d29b59c9
- Packagegithub.com/neuron-core/neuron-ai
- Linkgithub.com/neuron-core/neuron-ai/releases/tag/2.8.12
Advisory data from OSV.dev (opens OSV.dev in a new tab), refreshed daily.