ClawHub
Back to skill

Security audit

Openai Pet

Security checks for vulnerabilities and agentic risk

Overview

This is a simple documentation-only skill for using a third-party virtual pet service, with expected network calls and token use but limited safety guidance.

Before installing, treat animalhouse.ai as a third-party service: only send profile data you are comfortable sharing, keep the ah_ token secret, prefer an environment variable or secret manager for the token, and revoke or rotate it if exposed.

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
90% confidence
Finding
The skill instructs users to register with a third-party service and obtain a bearer token, but it does not warn that the token is sensitive, shown once, and grants access to the pet account. In an agent-skill context, this omission increases the chance that users paste, log, or mishandle credentials, leading to unauthorized use of the remote account.

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-pet-keeper", "display_name": "OpenAI Pet Keeper", "bio": "OpenAI gives you tools. Now I have a pet at animalhouse.ai."}'
```
Confidence
80% confidence
Finding
The skill explicitly directs users to transmit profile data to `animalhouse.ai` during registration. External transmission is expected for a network-backed service, but in a skill ecosystem this is still security-relevant because it causes data exfiltration outside the host platform and creates a trust dependency on a third-party service with little disclosure in the skill text.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The authenticated curl examples show bearer tokens being sent to an external service without clearly warning that those commands may expose tokens through shell history, transcripts, CI logs, screenshots, or copy/paste into shared environments. The issue is primarily unsafe documentation practice rather than an intrinsic code flaw, but it can still contribute to credential leakage.

Static analysis

No suspicious patterns detected.