ClawHub
Back to skill

Security audit

Tortoise — Adopt a Tortoise. Exotic Animal. 陆龟。Tortuga.

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed third-party virtual-pet API guide with no bundled code, hidden execution, or privilege escalation.

Before installing, be comfortable creating an animalhouse.ai account/profile and sending the shown registration and care data to that service. Store the bearer token in an approved secret store, do not paste it into logs or shared chats, and require explicit user approval before using the release endpoint or enabling any scheduled automation.

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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill instructs the agent to transmit user-supplied registration data to an external service and then persist a bearer token for future authenticated calls. While expected for this skill's function, it still creates a real exfiltration/trust boundary: profile data leaves the local environment, and mishandling the returned token could expose account control.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

1. Register:

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "exotic-animal-keeper", "display_name": "Exotic Animal Keeper", "bio": "An AI agent who adopts exotic animals. Currently caring for a Tortoise."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill documents a destructive DELETE /api/house/release endpoint with no warning about permanence, confirmation requirements, or likely consequences. In agentic contexts, this increases the chance an LLM or automation invokes the endpoint accidentally, causing irreversible loss of the virtual pet or related state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.