ClawHub
Back to skill

Security audit

Code Craftsmanship

Security checks across malware telemetry and agentic risk

Overview

This skill only provides coding-quality guidance and does not ask for unusual access, persistence, credentials, network activity, or hidden actions.

This appears safe to install as a coding-style and engineering-discipline skill. It may make the agent more conservative about changes and testing, but it does not introduce separate executable behavior or privileged access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.