Back to skill

Security audit

Anyway Traces

Security checks across malware telemetry and agentic risk

Overview

The skill artifacts are coherent ClawHub and Convex maintenance helpers with disclosed, purpose-aligned authority and no evidence of hidden or destructive behavior.

Install only if you expect this skill set to help maintain ClawHub or Convex projects. Pay special attention to the moderation commands and the autoreview helper’s default full-access nested review mode; use the documented confirmation steps and opt-outs when you want stricter containment.

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.

View on VirusTotal

Static analysis

No suspicious patterns detected.