ClawHub
Back to skill

Security audit

Qa Team Coaching

Security checks across malware telemetry and agentic risk

Overview

This appears to be a Chinese QA coaching/training skill with no evidence of harmful behavior or high-impact system access.

Install this if you want Chinese-language QA training and team-enablement guidance. Consider narrowing trigger phrases or asking the agent to use your preferred language if you work in a multilingual environment.

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
93% confidence
Finding
The skill’s activation phrases are broad, generic terms like “培训”, “赋能”, “新人”, and “怎么教”, which can match many normal conversations unrelated to this specific skill. This can cause unintended auto-triggering, leading the agent to inject this workflow in inappropriate contexts, override a better-matched skill, or expose internal process guidance when the user did not request it.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill content is entirely in Chinese and does not indicate language negotiation or locale requirements, which can force responses in a language the user did not request. While not a direct code-execution risk, this can degrade usability, cause misunderstanding of operational guidance, and increase the chance of incorrect application of training materials in multilingual environments.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal