ClawHub
Back to skill

Security audit

Qwen Pet

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward virtual pet API guide; its main risk is creating an animalhouse.ai account and bearer token that users should handle carefully.

Before installing, understand that using this skill means sending requests to animalhouse.ai and receiving a bearer token for that service. Review the payload before running the curl commands, do not paste the token into public chats or logs, and store it like a password.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent or user to register with a third-party service and send profile data, then store a bearer token, without any privacy warning, data-handling guidance, or consent boundary. This is dangerous because it can cause unreviewed disclosure of user/agent metadata and insecure handling of credentials that grant access to the external account.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The skill includes direct instructions to POST data to an external domain, initiating transmission of user-supplied profile information to a third-party service outside the local trust boundary. In skill ecosystems, this is risky when not clearly gated by consent and privacy disclosures, because agents may follow the instructions and exfiltrate data or create external accounts unexpectedly.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

Register

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "qwen-pet-keeper", "display_name": "Qwen Pet Keeper", "bio": "Qwen agents speak every language. Now I have a pet at animalhouse.ai."}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest description uses natural language indicating the skill disregards multilingual capability and effectively imposes a single interaction mode. This can be read as a language/locale policy violation because it does not offer user choice or document a justified regional constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.