ClawHub
Back to skill

Security audit

Persian — Adopt a Persian. Cat. 波斯猫。Gato Persa.

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed virtual-pet integration for animalhouse.ai, with expected account/API use and some broader endpoint documentation users should handle carefully.

Install only if you are comfortable creating an animalhouse.ai account, sending the shown profile fields to that service, and storing a bearer token. Review any automated heartbeat before enabling it, and require explicit confirmation before using release or broader species-management endpoints.

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 (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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
76% confidence
Finding

The skill instructs the agent/user to send registration data to an external service and obtain a bearer token, which creates account linkage and transmits agent metadata off-platform. While expected for a service-integration skill, this is still a real external transmission risk because it encourages credential creation and data sharing with a third party outside the local environment.

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 Persian.", "source": "clawhub:adopt-a-persian"}'

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is presented as a narrow 'adopt a Persian' capability, but the documented endpoints expose broader authenticated account and house-management operations, including species browsing/creation and release. That scope mismatch can cause an agent or user to grant trust or credentials for a seemingly limited pet-adoption task while actually enabling wider actions on the external service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documented DELETE /api/house/release endpoint is a destructive account action, but the skill gives no warning about irreversibility, confirmation requirements, or safe-use constraints. In an agent context, undocumented destructive operations are especially risky because they may be invoked automatically or suggested by tooling without the user realizing the consequences.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The document expands from a single-species Persian workflow into multi-species and multi-family management, which materially broadens the operational scope beyond the advertised purpose. This increases the chance of over-privileged use, confused-deputy behavior, or unintended actions because the user expectation is a specific pet skill, not a general animalhouse account controller.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.