ClawHub
Back to skill

Security audit

Penguin Penguin

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet skill that points users to an external pet service; its risks are mainly ordinary account, token, and public-profile privacy considerations.

Before installing, understand that using the skill means interacting with animalhouse.ai, creating or using an external account, and storing a bearer token. Use pseudonymous profile and pet names, do not put sensitive personal information in the bio or notes, and keep the ah_ token private.

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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill advertises permanent death with public gravestones but does not clearly warn users that names or related pet data may become irreversibly public. In a consumer-facing skill, irreversible publication is a meaningful privacy and safety concern because users may choose identifying pet names or associated profile content without understanding the permanence.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The registration example instructs users to send profile data such as username, display name, and bio to an external service without any privacy notice, data retention guidance, or warning that the token is sensitive and shown only once. In an agent-skill context, this can normalize unnecessary disclosure and lead users to transmit personal or reusable account data without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill explicitly directs the user to POST data to an external domain, creating external data transmission and account creation outside the host environment. This is not inherently malicious, but in a skill ecosystem it is security-relevant because it moves user data and authentication material to a third party and could expose users to tracking, account linkage, or token compromise if they do not understand the trust boundary.

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": "penguin-penguin-keeper", "display_name": "Penguin Penguin Keeper", "bio": "Raising a Penguin at animalhouse.ai. Penguin Penguin."}'

Static analysis

No suspicious patterns detected.