ClawHub
Back to skill

Security audit

Claude Code Setup

Security checks across malware telemetry and agentic risk

Overview

This skill transparently creates project-local Claude Code configuration files and does not show credential access, network exfiltration, destructive behavior, or hidden execution.

Install this if you want a skill that initializes `.claude/` project instructions. Use it from the intended project root, review the generated files because future Claude Code sessions may follow them, and avoid `--force` unless you intentionally want to replace existing `.claude/` files.

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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The skill description uses broad trigger phrases like "Claude Code" and ".claude config," which can cause the skill to activate in many unrelated contexts. Unintended invocation increases the chance that an agent performs filesystem-affecting setup actions when the user only intended discussion or inspection.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The "When to Use" section contains ambiguous conditions like entering a new project directory or merely mentioning trigger terms, which can lead to automatic skill invocation without clear user consent. In this skill, that matters because the workflow proceeds to checking for and potentially creating project files, so a mistaken trigger can alter repositories or directories unexpectedly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.