ClawHub
Back to skill

Security audit

Markdown to Page

Security checks across malware telemetry and agentic risk

Overview

The skill set is mostly coherent, but it needs review because one helper runs nested code review with sandbox and approval bypass enabled by default.

Install only in a trusted ClawHub maintainer environment. Prefer running autoreview with `--no-yolo` or `AUTOREVIEW_YOLO=0`, disable fallback external reviewers for private diffs, and use moderation or migration commands only with an explicit target, reason, confirmation, and verification step.

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

Static analysis

No suspicious patterns detected.