ClawHub
Back to skill

Security audit

Hugging Face CLI

Security checks across malware telemetry and agentic risk

Overview

The available skill artifacts are coherent development and ClawHub maintenance workflows with their powerful actions disclosed and scoped to user-directed tasks.

Install only if you want an agent to help with ClawHub/Convex development and maintainer workflows. Pay special attention before invoking moderation commands, proof publishing, external reviewer fallbacks, or the autoreview helper's default full-access nested Codex mode; use the documented confirmations and opt-outs when working with sensitive repositories or accounts.

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.