YourAITools MCP Hub

• Outcome: Pass
• Latest audit: Nov 2, 2026 · 11:48 AM UTC
• Version: 1.0.0

Overview

This skill clearly describes a remote tool service, discloses where inputs go, and requires approval before paid calls.

Install if you intend to use this external service. Submitted content reaches its operator, so exclude secrets and private material you do not want to share. Review current tool descriptions and approve prices before paid calls. The local instructions were fully inspected, but the live service, data-retention practices, and publisher claims remain unverified.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (6)

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 60% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 10)May include surrounding context.

md

openclaw:
    requires:
      bins:
        - curl
---

# YourAITools MCP Hub

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 18)May include surrounding context.

md

We built and run the YourAITools MCP Hub: one remote MCP server (streamable HTTP) that exposes our
agent APIs as 45 tools.

- MCP endpoint: `https://api.youraitools.co/mcp/hub`
- Docs: `https://api.youraitools.co/mcp/hub/README.md`
- Official MCP Registry name: `co.youraitools/hub`

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

Add the remote server to any MCP client that supports streamable HTTP, for example:

json

{ "mcpServers": { "youraitools": { "url": "https://api.youraitools.co/mcp/hub" } } }

List tools without any key:

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md

agent APIs as 45 tools.

- MCP endpoint: `https://api.youraitools.co/mcp/hub`
- Docs: `https://api.youraitools.co/mcp/hub/README.md`
- Official MCP Registry name: `co.youraitools/hub`

This skill contains instructions only: no code, no keys, and it never pays by itself.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

List tools without any key:

bash

curl -s -X POST https://api.youraitools.co/mcp/hub \
  -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% confidence

Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

md

Each tool's description says whether it has a free tier. Paid calls cost the same as the tool's own
paid route, with no hub fee, via prepaid credits (`Authorization: Bearer <key>`, see
https://api.youraitools.co/credits/) or x402 per call. Failed calls are not charged.
**Always ask the user to approve a paid call and its price first.** Never put keys in chat or in this skill.

## Safety