ClawHub
Back to skill

Security audit

jash

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent skill-authoring helper whose file creation and packaging behavior matches its stated purpose.

Install this only if you want help authoring skills. Use it in a dedicated working folder, review generated or edited SKILL.md files before packaging, and inspect the final .skill archive so unrelated or private files are not included.

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
80% confidence
Finding
The description is broad enough that the skill may trigger on common requests about creating or updating skills, causing it to load into contexts where it may not be the most appropriate tool. Over-broad triggering can increase attack surface by making file-writing, script-running, and packaging guidance more likely to be invoked in unrelated conversations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.