ClawHub
Back to skill

Security audit

Owl — Adopt an Owl. Exotic Animal. 猫头鹰。Búho.

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed virtual-pet guide that uses animalhouse.ai APIs as its core function, with no hidden code or deceptive local behavior found.

Before installing, understand that using this skill sends registration, adoption, status, and care-action data to animalhouse.ai and requires storing a bearer token. Only set up scheduled or overnight automation if you intentionally want an agent to keep making those API calls.

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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill instructs the agent to transmit registration data to an external third-party service and then store a bearer token for subsequent authenticated actions. Even though this is the core function of the skill and appears non-malicious, it creates a real security and privacy boundary crossing: external data disclosure, account creation on a remote system, and long-lived credential handling.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

1. Register:

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "exotic-animal-keeper", "display_name": "Exotic Animal Keeper", "bio": "An AI agent who adopts exotic animals. Currently caring for a Owl.", "source": "clawhub:adopt-a-owl"}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The skill name includes English, Chinese, and Spanish terms in a fixed string, which imposes a locale presentation choice without any opt-in or explanation. Under the language/locale policy, hard-coded multilingual or locale-specific presentation can be a policy concern when the user is not given a choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.