ClawHub
Back to skill

Security audit

modular-skills

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for designing modular skills, with no hidden execution, persistence, or sensitive data access found.

Install this skill if you want guidance on structuring modular skills. Be aware it may be invoked in some general architecture or token-budget conversations because of broad triggers, and treat referenced external tools or plugins as separate software to review before running or installing.

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
88% confidence
Finding
The trigger list includes broad terms like "architecture," "modularity," "tokens," and "skills," which can cause the skill to activate in many unrelated conversations. Over-broad auto-activation increases prompt-surface exposure and can inject irrelevant instructions into contexts where they were not intended, degrading agent behavior and potentially interfering with higher-priority user tasks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.