ClawHub
Back to skill

Security audit

justinX

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward third-party streaming-data MCP integration, but users should treat connected streams and broker credentials as sensitive.

Before installing, confirm JustinX is approved for the data you plan to connect. Avoid sending regulated, confidential, or production stream data unless you understand the provider's security, logging, and retention practices, and use secret storage or environment variables for real broker and API credentials.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill is explicitly designed to send live streaming data and authentication material to a third-party service, but it does not clearly warn users that broker messages, webhook payloads, and metadata may contain sensitive or regulated data. In an agent setting, this omission can cause users to connect internal telemetry or production streams without informed consent about privacy, retention, or external exposure.

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "mcpServers": {
    "justinx": {
      "url": "https://api.justinx.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "mcpServers": {
    "justinx": {
      "url": "https://api.justinx.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
{
  "mcpServers": {
    "justinx": {
      "url": "https://api.justinx.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The examples include plaintext usernames and passwords for MQTT and Kafka usage without warning users not to paste real secrets into prompts, shared configs, shell history, or logs. In LLM-assisted workflows, example secret fields are often copied verbatim into agent conversations or tool configs, increasing the chance of credential leakage to the model, MCP clients, or observability systems.

Static analysis

No suspicious patterns detected.