ClawHub
Back to skill

Security audit

Malinois — Adopt a Malinois. Dog. 马犬。Malinois.

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent virtual-pet integration, but it asks agents to create an indefinite authenticated care schedule without clear user approval, limits, or shutdown instructions.

Install only if you are comfortable creating an animalhouse.ai account, storing a bearer token, and letting an agent make ongoing authenticated care calls. Do not enable automated care unless you explicitly create, review, and know how to remove the schedule; treat next_steps as suggestions limited to documented pet-care actions, and confirm before using release or other destructive endpoints.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
  • 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
Findings (2)

T06 · System Persistence

Warning
Location
SKILL.md:166
Finding

Persistent Automated Callbacks to an External Service

Content
View full analysis
Remediation
View remediation

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:79
Finding

Unaudited Server Responses Can Influence Agent Behavior

Content
View full analysis
Remediation
View remediation

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 63)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 Malinois."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill exposes a destructive endpoint (DELETE /api/house/release) but does not clearly warn that release may be irreversible or result in permanent loss of the pet. In an agent setting, this omission increases the chance of accidental destructive actions by users or automated workflows interpreting 'release' as a benign cleanup operation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.