Security audit
mlx-whisper
Security checks across malware telemetry and agentic risk
Overview
This skill is a small, coherent guide for running local MLX Whisper transcription and shows no hidden or unrelated behavior.
Install only if you trust the mlx_whisper CLI and the Hugging Face model source. Expect the model to be cached locally and transcript or subtitle files to be written to the output locations you choose.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.