Skip to content

← Public intelligence

Packagist package

neuron-core/neuron-ai

Open actionable advisories and recorded vendor fixes. This public package view has no inventory attached and cannot establish whether your deployment is affected. A vendor fix never resolves your finding; verify your installed version and the source guidance.

Open advisories

2 actionable advisories, newest first. Withdrawn advisories and news are excluded. Coverage is partial.

  1. Critical, CVSS 9.4PackagistPublished

    Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)

    CVE-2025-67510 · GHSA-898v-775g-777c

    Affected
    • Packagist neuron-core/neuron-ai <= 2.8.11
    Fixed in
    2.8.12· Vendor fix available
    Issue
    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 +…

    Recommended action: Upgrade to 2.8.12 or later, then redeploy and verify.A vendor fix does not resolve your finding until you verify it in your own systems.

    Sources:github.comSource checked Evidence →
  2. High, CVSS 8.2PackagistPublished

    Neuron MySQLSelectTool “read-only” bypass via SELECT ... INTO OUTFILE (file write → potential RCE)

    CVE-2025-67509 · GHSA-j8g6-5gqc-mq36

    Affected
    • Packagist neuron-core/neuron-ai <= 2.8.11
    Fixed in
    2.8.12· Vendor fix available
    Issue
    Impact MySQLSelectTool is intended to be a read-only SQL tool (e.g., for LLM agent querying). However, validation based on the first keyword (e.g., SELECT) and a forbidden-keyword list does not block file-writing constructs such as INTO OUTFILE / INTO DUMPFILE. As a result, an attacker who can influence the tool input (e.g., prompt injection through a public agent endpoint) may be able to write arbitrary content to files on the DB server. If the MySQL/MariaDB account has the FILE privilege and server configuration permits writes to a useful location (e.g., a web-accessible directory), the impact can escalate to remote code execution on the application host (for example, by writing a PHP web shell). Who is impacted: Deployments that expose an agent using MySQLSelectTool to untrusted input and run with overly-permissive DB privileges/configuration. Patches Not patched in: 2.8.11 Fixed in: 2.8.12 Recommended fix direction: - Explicitly reject queries containing: INTO, OUTFILE, DUMPFILE,…

    Recommended action: Upgrade to 2.8.12 or later, then redeploy and verify.A vendor fix does not resolve your finding until you verify it in your own systems.

    Sources:github.comSource checked Evidence →