Mml
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only MML scene-building skill, with normal MML scripting and media features that users should review before publishing scenes.
Safe to install as a reference skill. Before using generated MML in a shared world, review scripts, event handlers, links, frames, and remote asset URLs, and clearly disclose any chat or position tracking to participants.
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
62/62 vendors flagged this skill as clean.