Main Agent Supervisor

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:17 PM UTC
• Version:
  0.1.0

Overview

This skill is a transparent markdown-only supervisor policy for reducing unnecessary agent permission prompts, with clear boundaries for risky actions.

Install this if you want an agent to ask fewer low-risk permission questions. Review the AUTO and CONFIRM rules first, and only enable the optional cron watchdog or custom hook pack if you are comfortable with persistent task monitoring in that workspace.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Low

• Confidence: 89% confidence
• Finding: The phrase "Use this skill in the current OpenClaw workspace with a phased design" describes when to use the skill only in very general terms and does not define explicit trigger phrases, scope boundaries, or exclusion conditions. In a markdown file, this creates an ambiguous activation condition because it is unclear what specific user requests should invoke the skill versus when it should stay inactive.

VirusTotal

66/66 vendors flagged this skill as clean.