ClawHub
Back to skill

Security audit

佩奇 Skill

Security checks across malware telemetry and agentic risk

Overview

The skill set is mostly coherent for ClawHub maintenance work, but it includes a review helper that runs nested Codex with approval and sandbox bypass enabled by default.

Install only if you trust the publisher and intend to use these skills for ClawHub maintainer/developer work. Before running autoreview, consider using `--no-yolo` or `AUTOREVIEW_YOLO=0`; before moderation or PR publishing commands, verify the exact target, account, and command because those workflows can change remote state.

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.