My Frontend Starter
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are coherent developer and moderation workflows with disclosed command use, and no scanner or artifact evidence shows malicious behavior.
Install only if you want these development and ClawHub moderation workflows. Use admin, GitHub, Convex, and full-access autoreview paths only in repositories and accounts you intend to affect; consider the autoreview helper's --no-yolo option when full sandbox bypass is not needed.
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
63/63 vendors flagged this skill as clean.