ClawHub
Back to skill

Security audit

ab-test-calculater

Security checks across malware telemetry and agentic risk

Overview

This skill is a local A/B test calculator with no evidence of hidden access, persistence, credential use, or data exfiltration.

Install this if you want a local helper for interpreting A/B test results. For important product or business decisions, treat the statistical output as decision support and verify assumptions, sample quality, and experiment design separately.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes phrases like "哪个版本更好" and "实验对比," which are generic comparative requests that can arise in ordinary conversation outside the intended A/B testing context. The file does not provide scope limits or negative examples to distinguish statistical experiment analysis from general advice requests.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The trigger section is explicitly labeled in Chinese and the listed activation phrases are predominantly Chinese, indicating a language-specific activation policy. The file does not state that users may choose their preferred language or that the Chinese-only trigger behavior is a justified regional constraint.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.