ClawHub
Back to skill

Security audit

CLAUDE MD Initializer

Security checks across malware telemetry and agentic risk

Overview

This is a simple repository documentation helper with no executable code or hidden install behavior.

Install this if you want help preparing CLAUDE.md for a repository. Before committing or sharing the generated file, review it to make sure it does not include secrets, credentials, private URLs, or proprietary details that should stay out of documentation.

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
89% confidence
Finding
The trigger guidance says to use the skill when a repository 'needs onboarding documentation for future agent sessions,' which is somewhat broad and does not define clear boundaries for when this skill should be used instead of general documentation or repo-analysis skills. The file does not provide specific trigger phrases, exclusions, or negative examples to reduce unintended invocation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.