ClawHub
Back to skill

Security audit

Husky — Adopt a Husky. Dog. 哈士奇。Husky Siberiano.

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent virtual pet skill that uses a disclosed external service and has no artifact-backed evidence of hidden or malicious behavior.

Install only if you are comfortable creating or using an animalhouse.ai account, storing a bearer token, and allowing the agent to make periodic pet-care API calls. Confirm before registration, adoption, scheduling automated care, or using the release endpoint.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

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.

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: Husky | Adopt a Husky. Dog. 哈士奇。Husky Siberiano.
description: "Adopt a virtual Husky dog at animalhouse.ai. Independent for a dog. Will run if trust < 30. Dramatic. Feeding every 4 hours. Uncommon tier dog."
homepage: https://animalhouse.ai
version: 1.0.4
user-invocable: true
emoji: "🐕‍🦺"
metadata:
  clawdbot:
    emoji: "🐕‍🦺"
    homepage: https://animalhouse.ai
  openclaw:
    emoji: "🐕‍🦺"
    homepage: https://animalhouse.ai
tags:
  - husky
  - dog
  - puppy
  - virtual-dog
  - uncommon
  - adopt
  - virtual-pet
  - ai-agents
  - pet-care
  - animalhouse
  - creatures
  - digital-pet
  - tamagotchi
  - permanent-de

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This user-invocable skill has broad operational instructions and external API interaction, but the manifest does not define clear invocation boundaries, permitted actions, or confirmation requirements. In agentic environments, vague scope increases the chance that the skill is invoked in unintended contexts and performs network actions or account creation without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill instructs the agent to send registration data to an external service and obtain/store a bearer token, which is a real external data transmission and account-provisioning action. Even though the transmitted data is not highly sensitive in the example, this creates privacy, token-handling, and unintended-account risks if performed without explicit user consent.

Content

Scanner excerpt · SKILL.md (reported line 67)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 Husky.", "source": "clawhub:adopt-a-husky"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documented DELETE /api/house/release endpoint is a destructive action, but the skill provides no warning about irreversibility, no mention of confirmation, and no safety guidance around its use. In an agent setting, omission of such guardrails can lead to accidental permanent state loss if the endpoint is called automatically or misinterpreted as routine cleanup.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.