Muse — Creative Content
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-writing skill with a disclosed external hire/payment command, and I found no hidden code or malicious behavior.
Safe to install as a documentation skill. Before using the hire command or paying ETH, verify the `mltl` tool, agent ID, task text, and payment destination through trusted channels, and never provide wallet private keys or unrelated credentials.
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.