Aishuo ClawHub Check

• Outcome: Pass
• Latest audit: Jun 3, 2026, 4:17 AM
• Version:
  0.0.1

Overview

This is a small, disclosed development smoke-test skill that documents a ClawHub publish check and contains no executable code.

Use this only as a disposable development integration test with a scoped ClawHub token. Expect it to publish a visible test record to ClawHub, and do not treat it as a production skill.

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 skill explicitly documents that the backend reads an integration token from the environment and performs an external upload to ClawHub, but it provides no user-facing warning, consent boundary, or restriction language around credential use and outbound transmission. Even though this appears to be a development verification skill rather than overtly malicious code, normalizing environment-secret access plus third-party publication increases the risk of unintended credential use or data being sent externally during execution.

VirusTotal

64/64 vendors flagged this skill as clean.