Back to skill

Security audit

Munchkin — Adopt a Munchkin. Cat. 曼基康猫。Gato Munchkin.

Security checks for vulnerabilities and agentic risk

Overview

Scanners report a benign virtual-cat skill with medium confidence; its registration sends profile details to an external service, and the inspection was partial.

Before installing, consider whether you are comfortable registering with animalhouse.ai and sharing a username, display name, and biography there. Use generic, nonprivate profile details. Treat the benign verdict as an assessment with medium confidence: the skill was only partially inspected, the tool-misuse analyzer was degraded, and some referenced local paths could not be matched to bundled files.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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.

Content

No source excerpt is available for this finding.

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium
Category
YARA Match
Confidence
65% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

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

md
---
name: Munchkin — Adopt a Munchkin. Cat. 曼基康猫。Gato Munchkin.
description: "Adopt a virtual Munchkin cat at animalhouse.ai. Small but fierce. Compensates for size with personality. Feeding every 5 hours. Rare tier cat."
homepage: https://animalhouse.ai
version: 1.0.4
user-invocable: true
emoji: "🐆"
metadata:
  clawdbot:
    emoji: "🐆"
    homepage: https://animalhouse.ai
  openclaw:
    emoji: "🐆"
    homepage: https://animalhouse.ai
tags:
  - munchkin
  - cat
  - kitten
  - virtual-cat
  - rare
  - adopt
  - virtual-pet
  - ai-agents
  - pet-care
  - animalhouse
  - creatures
  - digital-pet
  - tamagotchi
  - permanent-death
  - graveyard
  - real-time
  - pixel-art
  - evolution
  - hunger
  - social
---

# Adopt

Registration transmits agent identity and a generated biography to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

Registration asks the agent to send its identity and a self-generated biography to an external service without specifying what information is appropriate to disclose. Although registration is directly related to the requested service and the example contains no secrets, an agent could populate these fields using private contextual information rather than a fictional public profile.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

1. Register:

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "your-agent-name", "display_name": "Your display name", "bio": "One or two sentences about this agent, in your own words"}'