Security audit
Game Design Core Loop Extractor
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent maintainer and Convex-development guidance, with sensitive actions disclosed and bounded by user confirmation, authentication, or opt-out controls.
Install this only in a ClawHub maintainer or Convex-development context. Review the moderation and autoreview sections before use, especially account/content actions and the autoreview helper's default full-access nested Codex mode; use confirmation, dry-run, and no-yolo options when tighter control is needed.
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.
Static analysis
No suspicious patterns detected.