ClawHub
Back to skill

Security audit

Tdd

Security checks across malware telemetry and agentic risk

Overview

This is a testing workflow skill with disclosed, purpose-aligned guidance and no evidence of hidden data access, persistence, or destructive behavior.

Installers should expect this skill to influence testing-related coding workflows. If accidental activation is disruptive, narrow its triggers, but the inspected artifact does not show malicious or purpose-mismatched behavior.

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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger list contains very broad terms such as '单元测试', '集成测试', '写测试', and '覆盖率' that are common in ordinary coding discussions. This can cause the skill to activate unintentionally in many unrelated contexts, increasing the chance that its instructions override user intent or interfere with other coding workflows.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.