ClawHub

Multi Site Health Monitor

Security checks across malware telemetry and agentic risk

Overview

This monitoring skill is coherent, but it encourages automated production restarts, rollbacks, SSH commands, and broad third-party reporting without enough guardrails.

Install only if you intend to use it for operational monitoring and can tightly control its actions. Start in alert-only mode, use least-privilege tokens, avoid logging secrets or full response bodies, restrict third-party destinations, and require explicit human approval for SSH, restarts, scaling, rollbacks, or any action that can change live infrastructure.

SkillSpector

By NVIDIA
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 (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly promotes auto-restart, rollback triggers, and remote shell/SSH-based service actions, but it does not provide prominent safety guardrails, approval requirements, scope restrictions, or warnings about operational impact. In an agent setting, this can lead to unintended service disruption, unsafe automation against production systems, or execution of destructive commands based on incomplete or user-supplied monitoring conditions.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill is designed to send health, incident, and potentially sensitive operational metadata to third-party services including Slack, PagerDuty, Datadog, Google Sheets, WordPress-related endpoints, and cloud providers, yet it lacks an explicit privacy and data-handling warning. This increases the risk of leaking internal URLs, outage details, auth headers, service names, and infrastructure status to external platforms without informed user consent or minimization.

External Transmission

Medium
Category
Data Exfiltration
Content
**Example**: Monitor API health with custom authentication
```
Endpoint: https://api.example.com/health
Method: POST
Headers: 
  Authorization: Bearer YOUR_API_KEY
Confidence
84% confidence
Finding
https://api.example.com/

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal