Back to skill

Security audit

Cgroup

Security checks across malware telemetry and agentic risk

Overview

The reviewed artifacts are coherent repo-local workflow guidance for ClawHub and Convex maintenance, with sensitive actions disclosed and scoped to user-directed commands.

Install only if you want repo-local ClawHub and Convex automation. Review the moderation and autoreview workflows before use, because they can affect GitHub/ClawHub state or run review tools with broad local access when explicitly invoked.

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

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.