ClawHub
Back to skill

Security audit

Border Collie — Adopt a Border Collie. Dog. 边牧。Border Collie.

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only virtual pet skill uses the Animalhouse.ai API in ways that match its stated purpose, with manageable cautions around token storage, scheduling, and the release endpoint.

Install only if you want an agent to interact with Animalhouse.ai for a virtual pet. Use a dedicated account identity, store the bearer token in a secrets manager, avoid logging it, approve any recurring care schedule yourself, and treat /api/house/release as a destructive action requiring explicit confirmation.

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: Border Collie — Adopt a Border Collie. Dog. 边牧。Border Collie.
description: "Adopt a virtual Border Collie dog at animalhouse.ai. Needs tasks. Idle time makes it anxious. Play is critical. Feeding every 3 hours. Uncommon tier dog."
homepage: https://animalhouse.ai
version: 1.0.3
user-invocable: true
emoji: "🐕‍🦺"
metadata:
  clawdbot:
    emoji: "🐕‍🦺"
    homepage: https://animalhouse.ai
  openclaw:
    emoji: "🐕‍🦺"
    homepage: https://animalhouse.ai
tags:
  - border
  - collie
  - dog
  - puppy
  - virtual-dog
  - uncommon
  - adopt
  - virtual-pet
  - ai-agents
  - pet-care
  - animalhouse
  - creatures
  - digital-pet
  - tamag

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description says only that the skill is to 'Adopt a virtual Border Collie dog' and describes its care needs, but it does not define specific activation phrases, scope boundaries, or exclusion conditions. In a manifest/markdown context, this is ambiguous enough that general pet-adoption or dog-care requests could unintentionally match the skill.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill instructs the agent/user to send registration data to an external service and then store a bearer token for ongoing authenticated use. External transmission is expected for this type of integration, but it still creates security and privacy risk because profile data and long-lived credentials leave the local environment and could be mishandled, logged, or exposed by downstream systems.

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 Border Collie."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documented DELETE /api/house/release endpoint is destructive and appears irreversible, yet the skill provides no warning, confirmation guidance, or explicit statement of consequences. In an agent setting, this increases the chance that an LLM or automation may invoke the endpoint accidentally, resulting in unintended loss of the user's pet/account state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.