Skill Publish
Security checks across malware telemetry and agentic risk
Overview
This is a straightforward publishing helper that asks the agent to sanitize content and get explicit approval before running ClawHub publish commands.
Use this only when you are comfortable letting an agent prepare content for public publication. Before approving, inspect the publish folder, file list, slug, name, version, and sanitized content, and run the ClawHub CLI only in an environment you trust.
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
66/66 vendors flagged this skill as clean.