ClawHub
Back to skill

Security audit

Drift — Adopt a Drift. AI-Native Pet. 漂流。Deriva.

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent guide for using a third-party virtual pet API, with expected network calls and token use disclosed in the instructions.

Install only if you are comfortable sending pet account details, care actions, prompts, and optional notes to animalhouse.ai. Treat YOUR_TOKEN like a password, avoid putting sensitive information in bio or notes fields, and only enable scheduled care if you want recurring authenticated API calls.

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
90% confidence
Finding

The skill instructs the agent to send registration data and later authenticated requests to an external service, including persistent bearer-token use. In an agent-skills ecosystem, this creates a real data-exfiltration and trust-boundary risk because user-provided content, operational metadata, and tokens may be transmitted to a third party without strong minimization or explicit consent language in the skill.

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 Drift.", "source": "clawhub:adopt-a-drift"}'

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file includes curl commands that send user-supplied profile data to a remote API and then use a bearer token for authenticated requests. While the token is mentioned, there is no broader user-facing warning about network transmission, third-party handling of submitted data, or the sensitivity of the Authorization header.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.