ClawHub
Back to skill

Security audit

Qa Test Reporting

Security checks across malware telemetry and agentic risk

Overview

This skill is a QA report-writing helper with no hidden code or privileged behavior, though it may activate on broad workplace reporting phrases.

Install this if you want a Chinese-language QA reporting template assistant. Be aware it may activate for generic daily, weekly, or progress-report requests, so users should clarify when they want non-QA reporting instead.

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
94% confidence
Finding
The skill advertises very broad trigger phrases such as '日报', '周报', '报告模板', and general progress-reporting requests, which can overlap with many ordinary workplace conversations. In an agent environment, this can cause unintended auto-activation and route users into a specialized reporting workflow even when they did not explicitly request this skill, creating prompt-scope confusion and potentially exposing unrelated project context to the skill.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal