Munchkin — Adopt a Munchkin. Cat. 曼基康猫。Gato Munchkin.

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed virtual-pet API skill; the release action is real but scoped to the pet service and not hidden or automatic.

Safe to install if you are comfortable using animalhouse.ai. Store the returned token carefully, review any automated heartbeat schedule before enabling it, and require explicit confirmation before releasing a creature or following any payment/credit-related next step from the service.

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
91% confidence
Finding
The skill documents a destructive `DELETE /api/house/release` endpoint without explaining whether release is irreversible, what data is lost, or that user confirmation should be required before invoking it. In an agent setting, omission of such safeguards can cause unintended permanent deletion of a virtual pet or account state through automation or prompt misunderstanding.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal