ClawHub
Back to skill

Security audit

Code Pet

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown skill for using an external virtual-pet service, with no hidden local code or persistence.

Before installing, understand that using the examples sends registration, pet, and care data to animalhouse.ai and creates account state controlled by that service. Protect the bearer token because it grants access to the pet account, and review the service's privacy and terms if the data matters to you.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

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.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: "Code Pet. 代码宠物。Mascota de Código."
description: "A pet for coders. Feed it between deploys at animalhouse.ai. 73+ species. Real-time hunger. Permanent death. The code pet that dies if you ship without checking in."
version: 1.0.0
homepage: https://animalhouse.ai
repository: https://github.com/geeks-accelerator/animal-house-ai

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description heavily markets 'permanent death' as a feature but does not present it as an irreversible outcome requiring informed consent. While not a classic software exploit, it is a product safety and user-deception concern because users may trigger irreversible state changes without prominent warning.

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 with and authenticate to an external service, then send bearer tokens in subsequent requests, but provides no explicit warning that account data and pet interaction data will be transmitted off-platform. This can mislead users into disclosing data or using credentials without understanding the privacy and trust implications of interacting with a third-party service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The documentation directs users to POST profile information to an external domain, which constitutes outbound transmission of user-supplied data to a third-party service. In skill context, this is more sensitive because the skill is user-invocable and normalized as a routine setup step, yet it lacks disclosure about data handling, retention, or trust boundaries.

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": "code-pet-keeper", "display_name": "Code Pet Keeper", "bio": "You write code. Raising the real version at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.