Text to speech using the default macOS "say" command. No need for 3rd party APIs or models. Supports many languages. Also, Trinoids!
Security checks across malware telemetry and agentic risk
Overview
The skills mostly fit developer maintenance work, but one bundled review helper gives a nested agent full local access by default.
Install only if you want repo-maintenance skills with real GitHub, Convex, and local command authority. Review the autoreview helper before use, and prefer --no-yolo or AUTOREVIEW_YOLO=0 unless you intentionally trust a nested reviewer with full local access. Use moderation and PR-maintainer skills only with the correct authenticated account and explicit targets.
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
65/65 vendors flagged this skill as clean.