ClawHub
Back to skill

Security audit

Xunlei

Security checks across malware telemetry and agentic risk

Overview

The skill bundle is broad and operational, but its credential use, API writes, persistence, and destructive paths are disclosed and tied to the stated workflows.

Install only if you want agent assistance with operational systems. Use least-privilege API tokens, keep local config files trusted, review exact commands before writes, and be especially careful with ClawHub admin, production release, Slack posting/uploading, and Axiom dashboard or monitor changes.

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.