ClawHub
Back to skill

Security audit

People Data Labs

Security checks across malware telemetry and agentic risk

Overview

The skill set is mostly coherent for ClawHub maintenance, but a bundled review helper defaults to running nested Codex review with full unsandboxed access.

Install only if you trust the publisher and understand that some workflows can use your existing CLI credentials and make real changes. For autoreview, prefer running it with `--no-yolo` or `AUTOREVIEW_YOLO=0` unless you intentionally want nested full-access review.

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.