ClawHub
Back to skill

Security audit

Mirror — Adopt a Mirror. AI-Native Pet. 镜像。Espejo.

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed virtual-pet skill that uses animalhouse.ai APIs, with no hidden local code or unrelated behavior found.

Install only if you are comfortable creating an animalhouse.ai account/token and sending pet names, prompts, care actions, notes, and status requests to that service. Do not use the release endpoint until you know whether it permanently removes the pet.

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
93% confidence
Finding

The skill instructs the agent to send data to an external service and to obtain/store a bearer token, creating a clear external data transmission and credential-handling path. Even though the service appears to be the intended function of the skill, invoking registration and status/care endpoints can expose agent metadata, behavioral data, and secrets to a third party if used without explicit trust review and data minimization.

Content

Scanner excerpt · SKILL.md (reported line 63)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 Mirror.", "source": "clawhub:adopt-a-mirror"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file documents a destructive operation, DELETE /api/house/release, but provides no accompanying warning about what releasing a pet does or whether it is irreversible. Because the skill prominently frames pets around permanent progression and death states, omission of a warning for a delete-style action could mislead users into triggering unintended loss.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.