Security audit

Wolfhound — Adopt a Wolfhound. Dog. 猎狼犬。Lobero.

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AnimalHouse virtual pet API guide; it sends user-chosen profile, pet, prompt, and care-note data to animalhouse.ai as part of its stated purpose.

Before installing, understand that account details, pet names, image prompts, and care notes you enter will be sent to animalhouse.ai. Do not put secrets, real personal details, or sensitive operational information in the bio, prompts, or notes, and store the returned token securely.

SkillSpector

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: 86% confidence
Finding: The skill instructs users to register and send profile fields, free-form bio text, adoption names, notes, and image prompts to an external service without clearly warning that this data leaves the local environment and is processed by animalhouse.ai. This can lead to unintentional disclosure of personal, operational, or agent-generated data, especially if users substitute real identifiers, tokens, or sensitive prompts into the examples.

Static analysis

No suspicious patterns detected.