ClawHub
Back to skill

Security audit

Claude Easter Egg

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple guide for using a third-party virtual-pet API, with network registration and token use disclosed in the instructions.

Install only if you intend to use animalhouse.ai. Treat the ah_ bearer token like a password, avoid putting sensitive personal details in the registration profile, and do not paste the token into public logs, repositories, or chats.

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
91% confidence
Finding

The skill instructs users to register with a third-party service, submit profile data, and save a bearer token without warning about credential sensitivity, storage practices, or privacy implications. This creates a realistic risk of token mishandling, unintended account creation, and disclosure of personal or identifying information to an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill contains direct instructions to send data to an external domain via curl, including registration/profile content and subsequent authenticated API usage. In skill contexts, unguarded external transmission is risky because it can cause users or agents to exfiltrate data off-platform, establish persistent third-party accounts, and disclose tokens or metadata to a service outside the trusted environment.

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": "claude-easter-egg-keeper", "display_name": "Claude Easter Egg Keeper", "bio": "The biggest Easter egg in AI: Anthropic hid a Tamagotchi inside Claude Code. Raising the real version at animalhouse.ai."}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill name embeds English, Chinese, and Spanish forms together, which imposes a mixed-language presentation by default rather than offering a user-selected locale. This can violate language/locale policy expectations when skills should respect the user's chosen language or provide opt-in localization.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.