ClawHub
Back to skill

Security audit

Runtime Verifier

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only skill for proving changes by running software, and its live-runtime behavior is disclosed and aligned with that purpose.

Install is reasonable if you want an agent to verify changes in a real running app or CLI. Before using it, specify the exact target, expected behavior, and any commands or endpoints that must not mutate data; prefer local, test, or staging environments over production.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This markdown skill file instructs the agent to start services and run checks in a live environment, which can affect data, external systems, or system integrity. The description does not include any user-facing warning to use a safe/test environment or to avoid destructive actions during verification.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.