ClawHub
Back to skill

Security audit

Mood Tracker

Security checks across malware telemetry and agentic risk

Overview

The skill set is mostly coherent ClawHub maintainer guidance, but its autoreview helper defaults to running a nested Codex review with full filesystem and approval bypass permissions.

Install only if you are comfortable with ClawHub maintainer tooling that can use your local GitHub/ClawHub credentials. Before running the autoreview helper, prefer `--no-yolo` or set `AUTOREVIEW_YOLO=0` unless you intentionally want a nested Codex review with full filesystem access and no approval prompts.

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

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.