GitHub Advisoryadvisory · Packagist

GHSA-898v-775g-777c Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)

CRITICAL Published 2025-12-09 Modified 2025-12-11 Official page ↗
Aliases
CVE-2025-67510
Ecosystem
Packagist
Packages
neuron-core/neuron-ai
Severity
Critical
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:H
Weaknesses
CWE-250, CWE-284
Reviewed
2025-12-09

Affected packages

• Packagist neuron-core/neuron-ai: < 2.8.12 → fixed in 2.8.12

Description

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`/`UPDATE` on selected tables; forbid `DROP/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 `MySQLWriteTool` for public/untrusted agents. • Use a dedicated DB user with least privilege: • no `DROP`, no `ALTER`, no `GRANT`, 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).

Related

Alias · CVE (1)

  • CVE-2025-67510 Neuron is a PHP framework for creating and orchestrating AI Agents. vulnerability

Weakness · CWE (2)

  • CWE-250 Execution with Unnecessary Privileges weakness
  • CWE-284 Improper Access Control weakness

References