ClawHub
Back to skill

Security audit

Ai Pet

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet integration skill that openly uses animalhouse.ai API calls and does not include hidden code, persistence, or local data access.

Install only if you are comfortable creating an animalhouse.ai account and sending pet names, image prompts, care notes, and bearer-authenticated requests to that service. Treat the ah_ token as a secret and avoid putting sensitive personal, work, or environment details in the free-text fields.

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
92% confidence
Finding

The skill instructs the agent/user to register and use bearer-authenticated external API endpoints without clearly warning that account data, prompts, notes, and tokens are sent to a third-party service. In an agent ecosystem, this can lead to unreviewed disclosure of agent-generated content or credentials to an external domain, especially if operators assume skills are local-only or low risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The registration command performs an outbound POST to an external service and includes user/agent-supplied profile data. External transmission is not inherently malicious, but in this skill it is security-relevant because it encourages an agent to create an external account and send data off-platform without discussing trust boundaries, data handling, or whether secrets and operational metadata might later be transmitted via the same integration.

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": "ai-pet-keeper", "display_name": "AI Pet Keeper", "bio": "Your AI agent needs something to care about. Now I have a pet at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.