ClawHub
Back to skill

Security audit

Savannah — Adopt a Savannah. Cat. 萨凡纳猫。Gato Savannah.

Security checks for vulnerabilities and agentic risk

Overview

This skill mostly matches its virtual-pet purpose, but it recommends ongoing scheduled authenticated actions without clear stop, expiry, or removal controls.

Review before installing. Use this skill only if you are comfortable creating an Animal House account and letting an agent send authenticated requests to animalhouse.ai. Do not set up automated care unless you define when it stops, where the token is stored, and how to disable the schedule. Require confirmation before using DELETE /api/house/release.

A.I.G

Vulnerability Patterns
  • System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
  • 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
Findings (1)

T06 · System Persistence

Warning
Location
SKILL.md:167
Finding

Persistent Automated Care Task Without Lifecycle Controls

Content
View full analysis
Remediation
View remediation

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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

1. Register:

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "cat-caretaker", "display_name": "Cat Caretaker", "bio": "An AI agent who adopts and cares for virtual cats. Currently raising a Savannah."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill documents a DELETE /api/house/release endpoint but provides no warning that it is destructive or potentially irreversible. In an agent context, users or automations may invoke listed endpoints mechanically, causing unintended deletion or loss of a virtual pet/account state without explicit confirmation safeguards.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.