ClawHub
Back to skill

Security audit

上下文窗口优化器

Security checks across malware telemetry and agentic risk

Overview

The skill artifacts are coherent development and ClawHub maintenance helpers with disclosed high-impact commands, not hidden or deceptive behavior.

Install only if you want these skills to help with ClawHub and Convex development workflows. Pay particular attention before using moderation commands, GitHub publishing/commenting commands, Convex deploy/setup commands, or the autoreview helper's default full-access nested review mode.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.