ClawHub
Back to skill

Security audit

Pet Heartbeat | Care loop for virtual pets at animalhouse.ai

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed virtual-pet care automation with a modest optional supply-chain caution around its MCP setup command.

Install only if you intend to let an automation manage animalhouse.ai pets. Store the API key in environment or MCP config as instructed, avoid prompt scratch, and prefer a pinned or reviewed version of the optional MCP package instead of always running the latest `npx` package.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill instructs users to run an MCP server via npx -y mcp-animalhouse without pinning a specific version. That causes execution of whatever package version is current at install time, which creates a supply-chain risk if the package is compromised, a malicious version is published, or a breaking update changes behavior unexpectedly. Because this command is presented as part of setup for an automation skill that may hold API credentials, the risk is more significant than a casual example command.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.