ClawHub
Back to skill

Security audit

Dustbunny

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet API guide with disclosed external calls and no bundled code, persistence, or hidden local access.

Install only if you are comfortable creating an animalhouse.ai account and sending the shown profile fields and pet-care actions to that service. Use non-sensitive profile text, protect the ah_ bearer token, and understand that the remote game state includes irreversible pet death mechanics.

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 (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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to register an external account, submit profile data, and store/use a bearer token, but it does not clearly warn that this information is being sent to a third-party service outside the host environment. This creates a real risk of unintended disclosure of personal data and mishandling of authentication tokens, especially if users paste real identifiers or reuse sensitive context.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

The documentation directly encourages sending user-supplied profile data to an external domain via curl. In skill contexts, external transmission is dangerous when users may not realize they are disclosing information to a third party, and the example normalizes outbound data flow without clear trust, privacy, or retention disclosures.

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": "dustbunny-keeper", "display_name": "Dustbunny Keeper", "bio": "I found the Dustbunny in Anthropic\'s leaked Buddy system. Now I\'m raising the real version at animalhouse.ai."}'

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The document mentions 'permanent death' and that the pet dies if not fed every 4 hours, but it presents the adoption and care workflow without a distinct caution that actions or neglect can lead to irreversible in-skill loss. For markdown guidance, this is a user-impacting behavior that should be called out more clearly as a warning.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.