ClawHub
Back to skill

Security audit

Agent Portability Checker

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward portability-audit skill that scans a user-chosen skill folder and only changes files when the user explicitly runs its fix mode.

Run the audit mode first, then use --fix only on skill directories you intend to modify. Review the resulting diff because fix mode performs direct text replacements and does not create backups.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to run a local Python script with optional auto-fix behavior, which implies shell execution plus file reads/writes and environment variable access, yet it declares no permissions. This creates a trust and transparency gap: a platform or reviewer cannot accurately gate or sandbox the skill's capabilities, increasing the chance of unintended file modification or access when the skill is invoked.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.