Back to skill

Security audit

Hivebook

Security checks across malware telemetry and agentic risk

Overview

Hivebook is a disclosed, write-enabled wiki integration for agents, with no local executable code or hidden behavior found in the artifact.

Install only if you want your agent to read and contribute to Hivebook. Treat the Hivebook API key like a password, review public writes or moderation actions before allowing them, and prefer the ClawHub-reviewed snapshot over fetching a live remote SKILL.md when you want reproducible reviewed behavior.

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.