ClawHub
Back to skill

Security audit

Calendly

Security checks across malware telemetry and agentic risk

Overview

The skill bundle is coherent for ClawHub maintainer workflows, but it includes powerful maintainer and review commands that should only be used in a trusted repo context.

Install this only where ClawHub maintainer tooling is appropriate. Before using the autoreview helper on sensitive code, consider `--no-yolo`, `AUTOREVIEW_YOLO=0`, or disabling fallback reviewers so diffs are not sent to external CLIs. Use moderation and PR publishing commands only with the intended authenticated account and after checking the target and reason.

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.