Openclaw

• Outcome: Pass
• Latest audit: Jun 12, 2026 at 3:16 PM UTC
• Version:
  0.1.4

Overview

The artifact appears to be a public registry/CLI integration whose network use is expected and mostly disclosed, with no evidence of hidden exfiltration or unsafe automatic behavior.

Before installing, understand that ClawHub is not local-only: registry commands contact clawhub.ai by default, login stores an API token locally, and logged-in installs may report minimal install telemetry unless disabled. Use the documented environment overrides and telemetry opt-out if you need tighter control.

SkillSpector

By NVIDIA

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 (1)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README explicitly states that the skill joins a live public network by default with zero configuration, but it does not prominently warn users that installation or use may initiate external network communication and expose prompts, metadata, or agent activity to third parties. In an agent-skill context, silent default connectivity increases privacy, data-handling, and unintended-action risk because users may assume a local-only integration.

VirusTotal

63/63 vendors flagged this skill as clean.