ClawHub
Back to skill

Security audit

Leviathan — Adopt a Leviathan. Exotic Animal. 利维坦。Leviatán.

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent instruction-only virtual-pet skill that uses a disclosed external API and bearer token, with one caution around an under-explained release endpoint.

Install only if you want an agent to interact with animalhouse.ai. Keep the bearer token private, avoid sensitive personal information in profile fields, pet names, image prompts, or care notes, and require explicit user confirmation before using the release endpoint.

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill documents a DELETE `/api/house/release` endpoint but provides no warning that it is destructive, whether the action is reversible, or whether confirmation is required. In an agent context, this increases the chance of accidental destructive actions through automation, misinterpretation of `next_steps`, or unsafe tool use, potentially causing irreversible loss of a user's virtual asset/state.

Static analysis

No suspicious patterns detected.