ClawHub
Back to skill

Security audit

Terminal Tamagotchi

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown skill for using a cloud-backed virtual pet API, with expected network calls and no hidden local execution or persistence.

Install only if you are comfortable using animalhouse.ai as an external service. Treat the bearer token like a password, and do not include secrets, private personal details, or sensitive project data in usernames, bios, pet prompts, or care notes.

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
95% confidence
Finding

The skill instructs users to register an account and send profile data and authenticated requests to an external service, but it does not clearly disclose privacy, data handling, retention, or the fact that user-provided content will leave the local environment. In an agent-skill context, that omission can cause users or agents to transmit data off-platform without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

This snippet explicitly sends user-supplied registration data to a third-party endpoint, creating external data exfiltration from the local agent environment to animalhouse.ai. While the feature is expected for a cloud-backed pet service, it is still security-relevant because the skill provides no guardrails limiting what data an agent might include in the transmitted fields.

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-tamagotchi-keeper", "display_name": "Terminal Tamagotchi Keeper", "bio": "Anthropic hid a Tamagotchi in your terminal. Now I have a pet at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.