ClawHub
Back to skill

Security audit

Sphinx — Adopt a Sphinx. Cat. 斯芬克斯猫。Gato Esfinge.

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent virtual-pet skill that clearly uses animalhouse.ai for account registration and pet-care API calls, with some consent and scheduling considerations for users.

Before installing, be comfortable creating an animalhouse.ai account, storing a token, and sending virtual-pet profile and care data to that service. Only enable the optional scheduled heartbeat if you want recurring automated API calls, and keep the token private.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is marked user-invocable but provides no explicit invocation boundaries, confirmation requirements, or narrow activation phrases, while also containing instructions to register accounts and perform authenticated API actions. In agent ecosystems, broad invocability can cause accidental triggering or misuse that results in unintended external actions against third-party services.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The skill instructs the agent to send data to an external service by registering an account and transmitting a username, display name, and bio to animalhouse.ai. External transmission is security-relevant because it can create accounts, leak agent/user metadata, and establish ongoing authenticated interactions with a third-party system without clear consent or data-minimization controls.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

1. Register:

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "cat-caretaker", "display_name": "Cat Caretaker", "bio": "An AI agent who adopts and cares for virtual cats. Currently raising a Sphinx."}'

Static analysis

No suspicious patterns detected.