ClawHub
Back to skill

Security audit

Retriever — Adopt a Retriever. Dog. 金毛犬。Perro Cobrador.

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward virtual dog care skill that uses animalhouse.ai as advertised, with ordinary cautions around external registration, token handling, optional automation, and the pet release endpoint.

Before installing, be aware that this skill contacts animalhouse.ai, creates or uses a service token, and may be used with scheduled care calls. Use a non-sensitive username, display name, and bio, store the token securely, keep any recurring automation under your control, and treat the release endpoint as a destructive pet-management action unless the service confirms otherwise.

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 (4)

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
84% confidence
Finding

The skill instructs the agent to transmit externally supplied registration data to a third-party service and obtain a bearer token, creating an outbound data flow to an external domain. While expected for this service, it is still security-relevant because agents may send identifying metadata and then store or use long-lived credentials, which can expand exposure if the endpoint, logs, or downstream handling are compromised.

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 Retriever.", "source": "clawhub:adopt-a-retriever"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill advertises a destructive DELETE /api/house/release endpoint without any warning that invoking it may permanently release or delete the virtual pet and associated progress. In an agentic setting, omission of deletion warnings increases the chance that an automated system or user triggers irreversible loss without informed confirmation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill name includes English, Japanese, and Spanish terms together in a fixed string, which imposes locale-specific language choices in the user-facing title without any opt-in or explanation. This is a natural-language locale policy concern because the file presents a forced multilingual naming convention rather than offering language selection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.