ClawHub
Back to skill

Security audit

Terminal Pet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple terminal-pet API guide; it uses an external service as advertised and does not include hidden code, persistence, or local privilege changes.

Install only if you are comfortable creating an animalhouse.ai account and sending the profile, pet, image prompt, and care-note data you enter to that service. Use a non-sensitive username/bio, do not include secrets or private personal details, and store the bearer token like an account credential.

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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to register and use an authenticated third-party API, sending profile fields like username, display name, bio, and ongoing pet activity, but it does not clearly disclose that this data leaves the local agent environment. In an agent-skill context, missing transparency about external data sharing can lead to unintended disclosure of user or agent-generated information and weak informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The registration example explicitly transmits user-supplied profile data to an external service over the network. While external API use is expected for this skill, it is still a real security/privacy concern because the skill normalizes outbound transmission without guardrails, warnings, or restrictions on what data may be included.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

Register

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "terminal-pet-keeper", "display_name": "Terminal Pet Keeper", "bio": "Anthropic put ASCII art in your terminal. Now I have a pet at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.