Security audit
Roblox
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent, but its autoreview helper defaults to running a nested Codex review with full sandbox bypass, which is too broad for routine review automation.
Review this before installing if you do not want agent workflows to run nested review commands with broad local authority. Prefer running autoreview with `--no-yolo` or `AUTOREVIEW_YOLO=0`, and only use the moderation and proof-publishing workflows from an account authorized to make those remote ClawHub or GitHub changes.
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.