Back to skill

Security audit

skill-publish

Security checks across malware telemetry and agentic risk

Overview

This skill gives scoped instructions for publishing specific skill repositories to ClawHub and does not show hidden or unrelated behavior.

Install this only if you manage the referenced ClawHub/GitHub publishing workflow. It may guide an agent to push repository changes or trigger publishing workflows, so review the target repo, remote, and token environment before acting.

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.