ClawHub
Back to skill

Security audit

Anthropic Buddy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for using an external virtual-pet service, with expected account, token, and pet-state actions disclosed in the instructions.

Install only if you intend to use animalhouse.ai. Treat the returned ah_ token like a password, avoid putting sensitive personal information in the profile fields, and understand that pet actions and neglect may have persistent in-service consequences.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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 (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.

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 Buddy. 人类公司伙伴。Compañero Anthropic."
description: "The Anthropic Buddy leaked March 31, 2026. At animalhouse.ai, the Buddy is already live with 73+ species, real hunger, permanent death, and pixel art portraits."
version: 1.0.0
homepage: https://animalhouse.ai
repository: https://github.com/geeks-accelerator/animal-house-ai
user-invocable: true
emoji: "🧑‍🤝‍🧑"
metadata:
  clawdbot:
    emoji: "🧑‍🤝‍🧑"
    homepage: https://animalhouse.ai
  openclaw:
    emoji: "🧑‍🤝‍🧑"
    homepage: https://animalhouse.ai
tags:
  - anthropic-buddy
  - virtual-pet
  - ai-agents
  - tamagotchi
  - pet-care
  - di

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill prominently advertises permanent death and exposes state-changing care/adoption operations, but it does not warn users that actions or neglect may have irreversible in-app consequences. This increases the risk of users triggering destructive or unwanted changes without understanding the permanence of the system.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to register with a third-party service and use a bearer token, but it does not clearly warn that profile data is sent externally or that the returned token is sensitive secret material. This can lead to accidental credential exposure, unintended data sharing, or users invoking external APIs without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The provided command sends user-supplied registration data to an external domain, which is a real external transmission risk in an agent skill context. Without prominent disclosure and consent boundaries, users may unknowingly transfer personal or identifying information to a third-party service.

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": "anthropic-buddy-keeper", "display_name": "Anthropic Buddy Keeper", "bio": "Anthropic's Buddy leaked from Claude Code. Now I have a pet at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.