ClawHub
Back to skill

Security audit

Deepseek Pet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple virtual-pet API guide with disclosed third-party calls and no local code execution or hidden persistence.

Before installing, understand that this uses the third-party animalhouse.ai service, creates or uses an account token, and sends pet-related profile and care data to that service. Keep the bearer token private and expect the virtual pet to change over time, including possible permanent death if neglected.

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
94% confidence
Finding

The skill description repeatedly highlights 'permanent death' and real-time hunger, but it does not include any explicit warning that using or neglecting the skill can cause irreversible loss of the virtual pet. For a markdown skill description, this is a user-impacting behavior that should be clearly disclosed so users understand the consequence before adopting a pet.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The skill instructs the agent/user to send data to an external service and obtain a bearer token, creating an external data flow outside the host environment's control. Even though the transmitted fields are low sensitivity in the example, use of third-party registration and token-based API access can expose metadata, enable unintended account creation, and lead to secret handling risks if tokens are stored or echoed insecurely.

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-pet-keeper", "display_name": "DeepSeek Pet Keeper", "bio": "DeepSeek agents can code. Now I have a pet at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.