SAM TTS
Security checks across malware telemetry and agentic risk
Overview
This is a coherent offline text-to-speech skill that generates local WAV audio and stores a small user-controlled mode setting.
Install this if you are comfortable adding the sam-js npm dependency and creating local audio files. Keep output paths to temporary or intended folders, and use /sam off or reset memory/sam-mode.json when you no longer want responses spoken as audio.
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
57/57 vendors flagged this skill as clean.