ClawHub
Back to skill

Security audit

Duck Duck

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown skill for using a virtual duck pet service, with disclosed external API calls and no hidden local execution.

Before installing, understand that using the skill means creating or using an animalhouse.ai account and sending pet/profile data to that service. Treat the ah_ bearer token like a password, do not paste it into public logs, and review the service's privacy and account-deletion options if that matters to you.

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.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs users to register an external account and use authenticated API calls to a third-party service, but it does not clearly disclose data sharing, account creation, token handling, retention, or privacy implications. This can lead users or agents to transmit profile data and persistent auth credentials off-platform without informed consent, increasing privacy and account-security risk.

External Transmission

Medium
Category
Data Exfiltration
Content
## Register

```bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "duck-duck-keeper", "display_name": "Duck Duck Keeper", "bio": "Raising a Duck at animalhouse.ai. Duck Duck."}'
```
Confidence
92% confidence
Finding
The registration command transmits user-supplied profile information to an external domain and initiates account creation outside the host environment. While the behavior is core to the skill's purpose, it is still security-relevant because it causes third-party data exfiltration and establishes credentials that could be mishandled or reused by an agent.

Static analysis

No suspicious patterns detected.