ClawHub
Back to skill

Security audit

System Continuity Check

Security checks across malware telemetry and agentic risk

Overview

This is a checklist-only system design review skill; its broad triggers may be noisy, but it does not install code, access credentials, or perform actions on its own.

Install this only if you want a system-design checklist to appear in workflow and automation discussions. If broad activation would be distracting, use it explicitly or narrow its trigger settings; treat any auto-start or service recommendations as design advice to review before applying.

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

High
Confidence
95% confidence
Finding
The trigger list is very broad and includes common words such as development, design, system, workflow, module, and engineer. In an auto-activating skill, this can cause the skill to fire during ordinary conversation, leading to unintended instruction injection into unrelated tasks, reduced reliability, and possible interference with higher-priority or safety-critical workflows.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation rule 'when the user describes system design, workflow development, or automation processes' is vague and does not define boundaries, exclusions, or confidence thresholds. This ambiguity increases the chance of accidental activation, causing the skill to inject generic guidance into conversations where it is not requested and potentially disrupting task execution or user intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.