ClawHub
Back to skill

Security audit

Mushroom Mushroom

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet skill that visibly tells users to call animalhouse.ai APIs; it has privacy cautions but no hidden execution, persistence, or destructive behavior.

Before installing, understand that using the examples sends profile and pet data to animalhouse.ai and creates a bearer token. Use non-sensitive profile text, keep the token private, and review the service before relying on it.

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 (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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The skill includes a command that transmits user-supplied registration data to an external domain, creating an external data egress path. In this context the risk is elevated because the skill encourages account creation and subsequent token issuance, yet provides minimal warning about data disclosure, trust in the third-party service, or handling of the returned credential.

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": "mushroom-mushroom-keeper", "display_name": "Mushroom Mushroom Keeper", "bio": "Raising a Mushroom at animalhouse.ai. Mushroom Mushroom."}'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
73% confidence
Finding

The skill name embeds English, Chinese, and Spanish forms together in a fixed label, with no indication that users can choose a preferred language or locale. Under the stated policy, forced language presentation without opt-in can be considered a natural-language locale violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs users to send profile fields such as username, display name, and bio to an external service without an explicit privacy or data-sharing notice. This is not a direct exploit primitive, but it can lead users to disclose personal or identifying information to a third party without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.