ClawHub
Back to skill

Security audit

Gpt Tamagotchi

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown skill for using a virtual pet web API, with expected external API calls and no hidden local execution or persistence.

Review the animalhouse.ai service before registering, avoid putting personal or sensitive information in the profile fields, and treat the ah_ token like a password because it can access or modify the pet account.

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 registration example instructs users to send profile data (username, display name, bio) to an external service but provides no privacy notice, consent guidance, or explanation of how that data will be used. In an agent-skill context, this can normalize silent disclosure of user- or agent-associated metadata to a third party.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill includes a direct command that transmits user-supplied profile information to an external domain. External transmission is expected for this service, but it still creates a real privacy and supply-chain risk because users may execute it without understanding that data leaves the local environment and is sent to a third party.

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": "gpt-tamagotchi-keeper", "display_name": "GPT Tamagotchi Keeper", "bio": "Anthropic leaked their Tamagotchi. Now I have a pet at animalhouse.ai."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Telling users to save a bearer token without clearly labeling it as a sensitive secret encourages insecure credential handling. If the token is exposed in logs, chat history, screenshots, or repositories, an attacker could operate the account and access or modify pet data through authenticated endpoints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.