ClawHub
Back to skill

Security audit

Skill Test

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local skill-quality checker; the only notable issue is broad trigger wording, not hidden or dangerous behavior.

Safe to install for evaluating skill packages. Use it on a specific target skill folder, review unfamiliar target scripts before any runtime testing, and be aware that its broad trigger examples may activate for general skill publication-readiness requests unless invoked 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

Medium
Confidence
90% confidence
Finding
The implicit trigger example is broad enough to match common release-readiness or quality-assessment requests, which can cause the skill to activate outside its intended scope. Overbroad activation increases the chance of unintended tool use, confusing routing behavior, and accidental evaluation of unrelated content during ordinary publishing workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.