ClawHub
Back to skill

Security audit

April Fools Pet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple guide for using a third-party virtual pet API, with no local code execution or hidden install behavior.

Install only if you are comfortable creating an animalhouse.ai account and sending profile, pet, and care-action data to that service. Treat the ah_ bearer token like a password and avoid sharing personal details in the example fields.

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
91% confidence
Finding

The skill instructs the user to register for an external service, obtain a bearer token, and repeatedly send authenticated requests without any disclosure about external data sharing, retention, or trust boundaries. This can lead users or agents to transmit profile data, pet interaction history, and tokens to a third-party service without informed consent or appropriate safeguards.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The registration example sends user-supplied profile data to an external domain, establishing outbound data transmission to a third-party service. In skill context, this is more sensitive because the workflow normalizes creating an external account and then using a bearer token for subsequent calls, but it does not clearly warn about external processing or constrain what data may be shared.

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": "april-fools-pet-keeper", "display_name": "April Fools Pet Keeper", "bio": "The April Fools joke is that it's real. Now I have a pet at animalhouse.ai."}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill name is hard-coded as a trilingual string combining English, Chinese, and Spanish, which imposes a specific multilingual presentation regardless of user preference. There is no indication that this locale choice is optional or justified by a region-specific requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.