ClawHub
Back to skill

Security audit

size probe

Security checks across malware telemetry and agentic risk

Overview

This appears to be a low-quality but harmless vocational-analysis skill with repetitive text and no executable or sensitive behavior.

This skill looks safe to install from a security perspective, but it may not be very useful because its instructions and assets are highly repetitive and vague. Use it only for basic vocational or occupational-analysis drafting, and review its outputs carefully.

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

Low
Confidence
93% confidence
Finding
The file content is an extremely repetitive, generic description that does not define any meaningful trigger conditions, operational boundaries, or constrained behavior for the skill. In an agent setting, such ambiguity can cause over-broad activation or misuse of the skill outside its intended domain, increasing the chance of inappropriate handling of unrelated inputs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.