Domain Logic Pattern Selector
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed set of ClawHub maintenance skills whose powerful actions are aligned with their stated developer and moderation purposes.
Install only if you want ClawHub maintainer workflows on this machine. Treat moderation commands, GitHub comments/labels, PR proof publishing, and the autoreview helper's default full-access nested review as powerful actions: review targets and commands before they run, use the documented no-yolo path when appropriate, and keep staff/API credentials limited to trusted environments.
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
65/65 vendors flagged this skill as clean.