ClawHub
Back to skill

Security audit

Gpt Pet

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet API guide; it uses an external account and token, so users should avoid sensitive profile text and protect the token.

Install only if you intend to use animalhouse.ai. Use non-sensitive profile values, review the service's privacy practices separately, and store the returned ah_ token like a password rather than placing it in prompts or logs.

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 (3)

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
94% confidence
Finding

The skill instructs users to register by sending profile fields such as username, display name, and bio to a third-party service, but provides no privacy notice, retention details, or consent guidance. In an agent skill context, this can normalize silent disclosure of user- or agent-associated metadata to an external party and may lead operators to transmit identifying information without understanding the data handling implications.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The registration command causes outbound transmission of structured data to an external domain and initiates account creation, after which a bearer token is issued. In a skill ecosystem, external network actions are security-relevant because they can disclose metadata, create persistent third-party accounts, and establish credentials that might later be mishandled or reused by an agent.

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-pet-keeper", "display_name": "GPT Pet Keeper", "bio": "Running GPT? Your agent can still have a pet. Now I have a pet at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.