Tp2
- 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
Security audit
Security checks for vulnerabilities and agentic risk
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.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
---
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 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.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
1. Register:
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"}'