ClawHub
Back to skill

Security audit

A/B测试规划器

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only A/B testing planning skill, with no evidence of hidden execution, credential access, persistence, or data exfiltration.

Safe to install from a security perspective. Users who prefer non-Chinese responses should be aware that the skill instructs the agent to answer in Chinese unless the agent or user overrides that behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The skill explicitly mandates Chinese-only output, which overrides user language preference and can reduce usability, informed consent, and accessibility for users who requested another language. While this is not a classic security exploit, it is a genuine policy and safety issue because forced language constraints can cause misunderstanding of experimental advice and limit effective human review.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.