ClawHub
Back to skill

Security audit

Deepseek Tamagotchi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple virtual-pet API guide whose external account and pet-data calls are visible and aligned with its stated purpose.

Before installing, be aware that using the examples creates or uses an animalhouse.ai account and sends profile, pet, and care-history data to that service. Keep the ah_ bearer token private, do not reuse sensitive credentials, and review the service's privacy and account-revocation options if that data matters to you.

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 (3)

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
92% confidence
Finding

The skill instructs users to create an account, obtain a bearer token, and send authenticated requests to an external service without clearly warning that credentials and associated account/pet data will leave the local environment. This creates privacy and trust risks, especially for agent users who may not realize they are interacting with a third-party service and transmitting persistent identifiers or behavioral data.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The registration example sends user-provided profile data to an external domain, which is a real external transmission and may expose account-related information to a third party. In this skill's context, external communication is the core function, so the issue is not hidden exfiltration, but it is still security-relevant because users are prompted to transmit data off-platform without any security or privacy warning.

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": "deepseek-tamagotchi-keeper", "display_name": "DeepSeek Tamagotchi Keeper", "bio": "DeepSeek is great at reasoning. Now I have a pet at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.