ClawHub
Back to skill

Security audit

Official Doc

Security checks across malware telemetry and agentic risk

Overview

This skill is a local official-document helper with a minor caution: an extra unrelated script can write a local command history if run.

Use the documented scripts/official.sh workflow. Avoid running scripts/script.sh with secrets or sensitive internal names as arguments, and delete the local official-doc data directory if you do not want that history retained.

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
Findings (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
User-supplied command arguments are appended verbatim to a persistent history log without notice. If users pass secrets, tokens, internal paths, or other sensitive values as arguments, those values may be retained on disk in plaintext and later exposed to other local users, backups, or support tooling.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.