Security audit
Asset Ingest Guide
Security checks across malware telemetry and agentic risk
Overview
This is a small reference skill for demonstrating an asset publishing workflow and does not include hidden execution, credential handling, or privileged behavior.
This appears safe to install as a reference/demo skill. It may guide a user through publishing a local skill to ClawHub, so users should still review any publish command they choose to run and confirm the intended destination and contents.
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.
Static analysis
No suspicious patterns detected.