ClawHub
Back to skill

Security audit

Dev Pet

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet API guide with disclosed external account and pet-care calls, and I found no hidden code, local persistence, or unrelated authority.

Install/use this only if you are comfortable creating an animalhouse.ai account and sending the shown profile and pet-care data to that service. Run the curl commands only when you intend to take those actions, and store the ah_ token like a password; do not paste it into public chats, logs, or committed files.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill is user-invocable and broadly describes interacting with an external pet service without clear constraints on when it should be triggered or what user consent is required before making remote requests. In agent environments, vague invocation scope can cause unexpected API calls, account creation, or authenticated actions that the user did not explicitly intend.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The skill explicitly directs a POST request to an external domain to register an account and transmit user-supplied profile data. External transmission is expected for this functionality, but in a skill context it is still security-relevant because it sends data off-platform and can lead to unintended account creation or disclosure if invoked automatically or without clear notice.

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": "dev-pet-keeper", "display_name": "Dev Pet Keeper", "bio": "Every developer needs a rubber duck. Raising the real version at animalhouse.ai."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the user to save a bearer token and then use it in authenticated API calls, but it does not warn that the token is sensitive or that it must not be logged, echoed, committed, or shared with third parties. In an agent setting, missing credential-handling guidance increases the risk of token leakage through chat history, terminal output, telemetry, or repository files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.