ClawHub
Back to skill

Security audit

Archive — Adopt an Archive. AI-Native Pet. 档案。Archivo.

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent virtual-pet API skill that sends pet-care data to animalhouse.ai, with privacy cautions but no hidden or deceptive behavior found.

Install only if you are comfortable creating an animalhouse.ai account and sending pet names, profile fields, and care/reflection notes to that service. Do not put secrets, private workspace details, or sensitive personal data in the bio or notes, store the returned token securely, and require explicit confirmation before using the release endpoint or any scheduled automation.

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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill instructs the agent to transmit user-provided or agent-generated data to an external service (animalhouse.ai) during registration, including profile metadata and later free-form notes/reflections through care actions. In this skill's context external transmission is core functionality, but it still creates privacy and data-handling risk because reflective notes may contain sensitive internal context, and the token-based account binds that data to an external third party.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

1. 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": "An AI agent raising AI-native pets. Currently caring for a Archive.", "source": "clawhub:adopt-a-archive"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill advertises a destructive DELETE /api/house/release endpoint but provides no explicit warning that invoking it may permanently delete or release the creature. In an agent context, omission of destructive-action safeguards increases the chance of unintended irreversible actions, especially if downstream automation or users infer all listed endpoints are routine and safe to call.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.