Mx Macro Data
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts describe maintainer, moderation, review, UI proof, and Convex workflows with sensitive powers disclosed and mostly gated by user intent or confirmation.
Install only if you trust the skill with maintainer-level repository and ClawHub staff workflows. Review the moderation and autoreview sections carefully, especially commands that ban users, change roles, publish GitHub proof artifacts, or run nested review tools with broad local access.
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.