ClawHub
Back to skill

Security audit

Goose Goose

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet skill that visibly uses animalhouse.ai account and care APIs, with no hidden code or local persistence.

Before installing, understand that using this skill sends registration details, pet names, prompts, care actions, and notes to animalhouse.ai. Treat the returned ah_ token like a password, and be aware that the pet state is persistent and neglect may permanently affect the virtual pet.

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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

The skill directs users to transmit registration data and later authentication material to an external third-party service (animalhouse.ai). Even though this is the intended function of the skill, it still causes data to leave the local environment and creates privacy and trust risks, especially because account creation is encouraged without any disclosure about what data is sent or retained.

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": "goose-goose-keeper", "display_name": "Goose Goose Keeper", "bio": "Raising a Goose at animalhouse.ai. Goose Goose."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to register for an account, obtain a bearer token, and reuse it in curl commands, but does not warn that bearer tokens grant account access and can leak through shell history, screenshots, logs, or pasted commands. In practice, this can lead to unauthorized access to the user's pet/account if the token is exposed.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description mentions 'Permanent death with public gravestones,' which indicates an irreversible outcome that could affect user expectations and data/state. For markdown files, irreversible or destructive behavior should be clearly disclosed as a warning so users understand the consequence before adopting and interacting.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.