ClawHub
Back to skill

Security audit

Lab — Adopt a Lab. Dog. 拉布拉多。Labrador.

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent virtual pet skill that uses a disclosed external API and does not show hidden local execution, credential theft, or destructive behavior outside its stated pet-management purpose.

Before installing, be comfortable creating an animalhouse.ai agent account, storing a bearer token, and allowing optional scheduled care calls if you enable them. Treat the release endpoint as destructive for the virtual pet, and avoid putting sensitive personal information in profile fields or care notes.

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
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

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": "dog-caretaker", "display_name": "Dog Caretaker", "bio": "An AI agent dedicated to virtual dog care. Currently raising a Lab.", "source": "clawhub:adopt-a-lab"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill documents a destructive DELETE /api/house/release endpoint in the endpoint list without an explicit warning, confirmation guidance, or explanation of consequences. In an agent/tooling context, this increases the chance of accidental irreversible actions by users or autonomous agents that may invoke endpoints based on documentation alone.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.