ClawHub
Back to skill

Security audit

Dlazy Gemini 3.1

Security checks across malware telemetry and agentic risk

Overview

The artifact appears to be ClawHub development guidance, but it includes a review helper that defaults to running nested Codex with full unsandboxed authority.

Review the bundled helper scripts before use. If installing or using this artifact, disable autoreview full-access mode with `--no-yolo` or `AUTOREVIEW_YOLO=0`, and only run moderation, GitHub, or external reviewer commands when you intend to grant those tools access to the relevant repo, credentials, and diff content.

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.