Skill Polisher

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  2.0.2

Overview

This is a Markdown-only skill for polishing ClawHub skill documentation, with disclosed file review and user approval before overwriting originals.

Review the proposed SKILL.md changes, reference files, and audit report before approving any overwrite. Do not give this polisher secrets; it should only preserve credential documentation from the target skill when that target legitimately needs it.

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

Medium

• Confidence: 95% confidence
• Finding: The skill’s suggested invocation phrases are broad natural-language editing requests like 'Make this skill look better on ClawHub' and 'Clean up these skills,' which can overlap with routine documentation or content-editing tasks. This can cause the agent to activate the skill in contexts where the user did not explicitly intend skill-polishing behavior, leading to inappropriate rewrites of SKILL.md content or unintended changes across a bundle.

VirusTotal

59/59 vendors flagged this skill as clean.