Back to skill

Security audit

Executing Plans

Security checks across malware telemetry and agentic risk

Overview

The artifacts are coherent developer workflow guidance for ClawHub and Convex, with powerful but disclosed review, moderation, and deployment-adjacent commands.

Install only if you want ClawHub-specific maintainer and Convex development workflows. Treat the moderation commands as admin-grade actions, and consider using the autoreview helper with --no-yolo or AUTOREVIEW_YOLO=0 in sensitive repositories; also be aware that fallback reviewer CLIs may receive generated diff 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

66/66 vendors flagged this skill as clean.

View on VirusTotal