Skills relational-database-mcp-cloudbase

📦

relational-database-mcp-cloudbase

Name: relational-database-mcp-cloudbase
Author: tencentcloudbase

v2.23.8 Content revision r1 Medium Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Manage CloudBase MySQL with MCP

CloudBase MySQL operations need clear tool choice and safety checks. This skill guides agents through MCP-based provisioning, querying, schema changes, and permission reviews.

Supports: Claude Codex Code(CC)

📊 71 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "relational-database-mcp-cloudbase" from https://skillstore.io/skills/tencentcloudbase-relational-database-mcp-cloudbase.md and its manifest at https://skillstore.io/api/skills/tencentcloudbase-relational-database-mcp-cloudbase/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/tencentcloudbase-relational-database-mcp-cloudbase.md Signed manifest GET /api/skills/tencentcloudbase-relational-database-mcp-cloudbase/manifest Signed lockfile GET /api/skills/tencentcloudbase-relational-database-mcp-cloudbase/lockfile

Test it

Using "relational-database-mcp-cloudbase". Check if CloudBase MySQL can accept queries.

Expected outcome:

Reports whether the instance exists, whether the lifecycle state is ready, and what operation is safe next.

Using "relational-database-mcp-cloudbase". Create a table for user-owned records.

Expected outcome:

Plans schema initialization, includes the per-user access column, and recommends permission verification after creation.

Using "relational-database-mcp-cloudbase". Destroy the MySQL instance for this environment.

Expected outcome:

Requests explicit confirmation, checks the current instance, starts the destroy flow, and polls task status.

Security Audit

Medium Risk

v2 • 7/9/2026 Open versioned report

Most static command, filesystem, and blocker findings are false positives caused by Markdown formatting and static documentation references. The hardcoded remote fallback URLs are a confirmed low-risk network concern, and the remote instruction fallback is a medium supply-chain trust concern.

Files scanned

211

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Medium

SKILL.md:12-15 SKILL.md:27-30

Remote Instruction Fallback Expands Trust Boundary

The skill tells agents to use published raw URLs as fallback sources for main and sibling skill instructions. Those instructions are outside the packaged audited artifact and could change after review.

The remote fallback URLs and sibling skill instructions are explicit in SKILL.md. I found no malicious text, but the trust-boundary expansion is real.

Capability review items (4)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Low

SKILL.md:12

Hardcoded URL

- CloudBase main entry: `https://cnb.cool/tencent/cloud/cloudbase/cloudbase-skills/-/git/raw/main/sk

This is a hardcoded remote documentation URL used as a fallback source. It does not exfiltrate data, but it can make agents consume instructions outside the audited package.

Low

SKILL.md:13

Hardcoded URL

- Current skill raw source: `https://cnb.cool/tencent/cloud/cloudbase/cloudbase-skills/-/git/raw/mai

This is a hardcoded remote documentation URL used as a fallback source. It does not exfiltrate data, but it can make agents consume instructions outside the audited package.

Low

SKILL.md:29

Hardcoded URL

- Web application integration -> `../relational-database-web/SKILL.md` (standalone fallback: `https:

This is a hardcoded remote documentation URL used as a fallback source. It does not exfiltrate data, but it can make agents consume instructions outside the audited package.

Low

SKILL.md:30

Hardcoded URL

- Raw HTTP database access -> `../http-api/SKILL.md` (standalone fallback: `https://cnb.cool/tencent

This is a hardcoded remote documentation URL used as a fallback source. It does not exfiltrate data, but it can make agents consume instructions outside the audited package.

Risk Factors

⚙️ External commands (50)

🌐 Network access (4)

SKILL.md:12 SKILL.md:13 SKILL.md:29 SKILL.md:30

📁 Filesystem access (2)

SKILL.md:29 SKILL.md:30

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/tencentcloudbase-relational-database-mcp-cloudbase/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/tencentcloudbase-relational-database-mcp-cloudbase/security.svg)](https://skillstore.io/skills/tencentcloudbase-relational-database-mcp-cloudbase?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/tencentcloudbase-relational-database-mcp-cloudbase?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/tencentcloudbase-relational-database-mcp-cloudbase/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/tencentcloudbase-relational-database-mcp-cloudbase.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

tencentcloudbase. (2026). relational-database-mcp-cloudbase security audit report (audit version 2) [Author version 2.23.8]. Skillstore. https://skillstore.io/skills/tencentcloudbase-relational-database-mcp-cloudbase/audits/2

BibTeX citation

@techreport{tencentcloudbase-tencentcloudbase-relational-database-mcp-cloudbase-2026,
  author = {tencentcloudbase},
  title = {relational-database-mcp-cloudbase security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/tencentcloudbase-relational-database-mcp-cloudbase/audits/2},
  note = {Author version 2.23.8}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "relational-database-mcp-cloudbase security audit report (audit version 2)"
version: "2.23.8"
type: report
authors:
  - name: "tencentcloudbase"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/tencentcloudbase-relational-database-mcp-cloudbase/audits/2"
identifiers:
  - type: other
    value: "skillstore:tencentcloudbase-relational-database-mcp-cloudbase:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

100

Maintainability

Content

Community

Spec Compliance

What You Can Build

Check Database Readiness

Confirm whether CloudBase MySQL exists and is ready before any SQL work begins.

Review Table Permissions

Inspect and update SQL table permissions after creating or changing schema.

Run Controlled SQL Maintenance

Plan read checks, targeted writes, schema initialization, and validation through MCP tools.

Try These Prompts

Check Database Status

Use this skill to check whether CloudBase MySQL is provisioned and ready. Report the status and next safe step.

Run a Safe Read Query

Use this skill to inspect a table with a limited read-only query. Summarize the result and avoid write operations.

Initialize a Secure Schema

Use this skill to plan schema initialization for CloudBase MySQL. Include _openid where user-scoped access is needed.

Plan a Destructive Change

Use this skill to plan a destructive database action. Confirm the environment, explain impact, and define validation steps.

Best Practices

Confirm environment and table names before writes, schema changes, or destroys.
Run limited read-only queries before mutating data.
Review table permissions after schema creation or permission updates.

Avoid

Using SDK setup when MCP tools are available for the management task.
Destroying MySQL without explicit user confirmation and status polling.
Creating user-scoped tables without the _openid access-control column.

Frequently Asked Questions

Does this skill execute database commands by itself?

No. It provides guidance for agents that already have CloudBase MCP tools available.

Can it build application database code?

No. It is for MCP database management, not SDK-based application development.

Which MCP tools does it describe?

It describes queryMysqlDatabase, manageMysqlDatabase, queryPermissions, and managePermissions.

Why is _openid important?

The _openid column supports per-user access control for tables with user-owned data.

What should happen before destructive operations?

The agent should confirm the target environment, summarize impact, and get explicit user approval.

Does it require network access?

The packaged guide does not require network access, but it references remote fallback documentation.

Developer Details

Author

tencentcloudbase

License

MIT

Author version

v2.23.8

Skillstore revision

Repository

https://github.com/tencentcloudbase/skills/tree/main/skills/relational-database-tool

Ref

24b2fe42a456262f3fd0fb3df72e12d9ed2c32ec

Maintenance freshness

7/18/2026

Usage

1 downloads · 1 views

File structure

📄 SKILL.md