Back to skill

Security audit

Activity Maps

Security checks across malware telemetry and agentic risk

Overview

The skill artifacts are coherent workflow helpers with disclosed command use and no evidence of hidden collection, persistence, or destructive behavior outside their stated purposes.

Install only if you intend to use ClawHub/Convex maintainer workflows. Review the moderation and autoreview sections carefully: they can perform account or public-repo actions and may send code diffs to configured review CLIs, but the artifacts disclose these behaviors and provide control points.

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.

View on VirusTotal

Static analysis

No suspicious patterns detected.