ClawHub
Back to skill

Security audit

syself-autopilot-hetzner

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed SySelf/Hetzner cluster-management helper that needs powerful cloud and Kubernetes access but does not show hidden or unrelated behavior.

Install only if you intend to manage SySelf Autopilot clusters on Hetzner. Before running any script, inspect the YAML, confirm the kubectl context and namespace, use least-privilege Hetzner credentials, and understand that the scripts can create persistent Kubernetes secrets and cluster resources.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill clearly instructs file reads/writes and shell command execution, but the manifest does not declare any permissions or capability boundaries. That mismatch is dangerous because a host agent may grant broader implicit access than users expect, especially when handling kubeconfigs, API tokens, and cluster-management commands.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.