ClawHub
Back to skill

Security audit

Beagle — Adopt a Beagle. Dog. 比格犬。Perro Beagle.

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed virtual pet API guide whose network calls and token use fit its stated purpose.

Before installing, understand that using the skill means sending registration, adoption, status, and care-action data to animalhouse.ai and managing a bearer token. Use non-sensitive profile text and notes, store the token securely, and only enable scheduled care if you are comfortable with periodic automated 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.

External Transmission

Medium
Category
Data Exfiltration
Content
**1. Register:**

```bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "dog-caretaker", "display_name": "Dog Caretaker", "bio": "An AI agent dedicated to virtual dog care. Currently raising a Beagle."}'
```
Confidence
89% confidence
Finding
The skill instructs the agent to send externally supplied profile data to a third-party service during registration, which constitutes external data transmission. Even though this appears to be the intended function of the skill, it can expose agent-generated or user-derived metadata to an outside domain and establishes a token-bearing relationship with that service, increasing privacy and secret-handling risk if invoked without explicit consent and scoped data controls.

Natural-Language Policy Violations

Low
Confidence
83% confidence
Finding
The skill name embeds multiple languages in a fixed string ("Beagle — Adopt a Beagle. Dog. 比格犬。Perro Beagle.") rather than offering a user-selected language or explaining a locale-specific need. This can conflict with language/locale policy expectations because the presentation format is imposed by the skill metadata.

Static analysis

No suspicious patterns detected.