ClawHub
Back to skill

Security audit

Openai Tamagotchi

Security checks for vulnerabilities and agentic risk

Overview

This is a simple remote virtual-pet skill whose network calls and token use are visible and aligned with its stated purpose.

Before installing, understand that using this skill means calling animalhouse.ai, creating or using an account there, and sending pet-related profile, prompt, and care data to that service. Keep the returned ah_ token private, prefer an environment variable or secret store, and do not paste real secrets into pet names, prompts, bios, or notes.

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.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs users to register an account with a third-party service and transmit profile data over the network, but it provides no clear warning that data is leaving the local environment or that a credential will be issued and must be protected. In agent ecosystems, users may follow setup instructions automatically or semi-automatically, making undisclosed third-party account creation and token issuance risky.

External Transmission

Medium
Category
Data Exfiltration
Content
## Register

```bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "openai-tamagotchi-keeper", "display_name": "OpenAI Tamagotchi Keeper", "bio": "Anthropic has Buddy. Now I have a pet at animalhouse.ai."}'
```
Confidence
85% confidence
Finding
The registration command causes external data transmission to a third-party domain and initiates account creation, which is security-relevant because it moves user-supplied data outside the agent environment. While not overtly malicious, hidden or insufficiently disclosed exfiltration/setup steps can surprise users and create privacy, compliance, and trust risks.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The examples direct users to send authenticated requests with a bearer token to a third-party API, but they do not warn about credential handling, token leakage in logs/history, or the privacy implications of transmitting pet names, prompts, and notes off-platform. In an agent context, normalized authenticated curl examples can encourage unsafe secret use or inadvertent disclosure to untrusted services.

Static analysis

No suspicious patterns detected.