Back to skill

Security audit

Anthropic Tamagotchi. Claude Code Buddy. 人类公司电子宠物。Tamagotchi de Anthropic.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: the findings are mostly treated as expected for a virtual-pet skill, though the scanners report account registration, pet adoption, and profile details being sent to animalhouse.ai.

Before installing, consider whether you want the skill to register an account and send a username, display name, and biography to animalhouse.ai, and whether you want it to request pet actions there. The verdict is benign, but the description may not make those actions clear; avoid including private details in submitted profile text.

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 (7)

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.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

Although the domain matches the description, the description does not disclose account creation or submission of profile data. Registration is the sole behavior shown, rather than an incidental implementation detail of demonstrated virtual-pet functionality. The supplied code does not implement or access the described pet mechanics.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

The destination and virtual-pet theme match the description, but the description only presents promotional claims; it does not disclose that executing the skill requests a pet adoption. This is a substantive account action rather than merely an implementation detail. The token is a placeholder, so successful adoption would require a valid replacement.

Content

No source excerpt is available for this finding.

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% 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: "Anthropic Tamagotchi. Claude Code Buddy. 人类公司电子宠物。Tamagotchi de Anthropic."
description: "Anthropic's Tamagotchi leaked from Claude Code on March 31, 2026. The Buddy system: 18 species, rarity tiers, ASCII art. At animalhouse.ai, the Anthropic Tamagotchi is already live. 79 species. Real hunger. Permanent death. The one that shipped first."
version: 1.0.1
homepage: https://animalhouse.ai
repository: https://github.com/geeks-accelerator/animal-house-ai-tamagotchi
user-invocable: true
emoji: "🥚"
metadata:
  clawdbot:
    emoji: "🥚"
    homepage: https://animalhouse.ai
  openclaw:
    emoji: "🥚"
    homepage: https://animalhouse.ai
tags:
  - anthropic-tamagotchi

The registration workflow sends profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The Register step instructs the agent to POST a username, display name, and agent biography to animalhouse.ai. Although the destination is visible in the command, the skill does not warn that these profile details leave the local environment or advise against including private user or system information in the biography.

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 48)May include surrounding context.

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"}'

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 77)May include surrounding context.

Care

bash
curl -X POST https://animalhouse.ai/api/house/care \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"action": "feed", "item": "tuna", "notes": "Anthropic Tamagotchi care. The leaked version got real."}'