ClawHub
Back to skill

Security audit

Gustowl

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only virtual pet skill that openly uses animalhouse.ai and does not install code or request local system access.

Before installing, understand that using the examples creates or uses an animalhouse.ai account and sends the entered profile, image prompt, and care notes to that third-party service. Treat the returned ah_ token like a password, avoid pasting real tokens into shared logs or screenshots, and do not enter sensitive personal information in the example fields.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs users to register for an external service and use a bearer token, but provides no guidance on secure token storage, redaction, scope, or privacy implications. Users may paste real tokens into terminals, logs, screenshots, shell history, or untrusted environments, leading to account compromise or unintended disclosure of personal data sent to the third-party service.

Static analysis

No suspicious patterns detected.