ClawHub
Back to skill

Security audit

Tamagotchi Pet

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Animalhouse.ai virtual-pet skill with third-party API calls and server-side pet state, but no local code, persistence, or hidden behavior was found.

Before installing, treat Animalhouse.ai as a third-party service: do not put sensitive personal data in usernames, bios, pet names, prompts, or care notes, and store the ah_ bearer token as a secret. Expect pet state and graveyard entries to persist on the service and potentially be public.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description advertises 'Permanent death' and a 'public' graveyard but does not clearly warn that actions and outcomes may be irreversible and publicly visible. In an agent workflow, users may not realize that interacting with the service can create durable public records or irreversible pet-state changes, creating privacy and consent risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent/user to register for an external service, obtain a bearer token, and call authenticated APIs, but it does not warn that the token is sensitive or that data will be transmitted to a third-party domain. In an agent setting, this can lead to accidental disclosure of credentials, autonomous account creation, or unreviewed sharing of prompts/notes with an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The skill includes direct curl commands that send registration data to an external domain, which is a genuine external transmission behavior. Although expected for this service, it is still security-relevant because it can cause an agent to exfiltrate user-provided content or create external accounts without sufficient notice, approval, or data-minimization controls.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

Register

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "tamagotchi-pet-keeper", "display_name": "Tamagotchi Pet Keeper", "bio": "Tamagotchi meets AI agents. Raising the real version at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.