ClawHub

Vmware Pilot

Security checks across malware telemetry and agentic risk

Overview

This VMware orchestration skill is aligned with its stated purpose, but it under-scopes safety controls for high-impact infrastructure changes.

Review generated and custom workflows before execution, do not assume rollback is automatic, restrict write access to ~/.vmware/workflows, protect ~/.vmware audit/baseline files, and treat kubeconfig outputs and workflow parameters as sensitive operational material.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
# Warn about missing approval gate
    if not has_approval:
        warnings.append(
            "No approval gate found — consider adding one before destructive steps"
        )

    # Warn about destructive steps before any approval gate
Confidence
96% confidence
Finding
No approval

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal