Local Llama TTS
Security checks across malware telemetry and agentic risk
Overview
This is a coherent local text-to-speech skill; the reported shell-quoting issue should be fixed, but the artifacts do not show hidden behavior or malicious intent.
Install only if you are comfortable running a local shell wrapper and llama-tts binary. Prefer trusted local model files, avoid passing untrusted speaker paths, and consider patching or reviewing scripts/tts-local.sh so user-controlled paths are quoted and passed safely.
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
63/63 vendors flagged this skill as clean.