Grok Code Review
Security checks across malware telemetry and agentic risk
Overview
This is a transparent ClawHub/Convex maintenance skill set with powerful but disclosed, user-directed workflows.
Install only in a ClawHub/Convex maintenance environment where you intend agents to use GitHub, Convex, moderation, and proof tooling. Review the autoreview full-access default and use --no-yolo if you do not want nested review to bypass sandbox prompts.
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
64/64 vendors flagged this skill as clean.