ClawHub
Back to skill

Security audit

linkedin-ads

Security checks across malware telemetry and agentic risk

Overview

This appears to be a coherent ClawHub maintainer skill bundle, but it asks for high-impact authority such as staff moderation actions and a default full-access nested code-review helper.

Install only in a trusted ClawHub maintainer environment. Before using moderation or PR-publishing workflows, verify the target, reason, account, and command; for autoreview, prefer the documented --no-yolo option when full local filesystem authority is not necessary.

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.