ClawHub
Back to skill

Security audit

Code Pet

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only virtual-pet API skill with no local code execution, but users should treat the service token like a password.

Use non-sensitive profile and pet text, store the returned ah_ token securely, avoid pasting it into shared chats/logs or committing it to files, and rotate or revoke it if exposed. VirusTotal was pending, but artifact review, static scan, and SkillSpector did not show malicious behavior.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
84% confidence
Finding
The skill instructs users to register, receive a bearer token, and use it for authenticated API calls, but provides minimal credential-handling guidance despite noting the token is shown only once. This increases the chance users will paste tokens into logs, shells, transcripts, or shared agent contexts, leading to account takeover for the external service.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.