Back to skill

Security audit

Interior Design

Security checks for vulnerabilities and agentic risk

Overview

This interior design skill is a coherent local planning aid with disclosed local project storage and no evidence of hidden, destructive, or credential-seeking behavior.

Before installing, be aware that the skill is meant to keep local notes about your rooms, budget, suppliers, and preferences in ~/interior-design/. Avoid adding anything more sensitive than needed, and review those local files if you share your machine or workspace.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Hidden Instructions

High
Category
Prompt Injection
Content
Priority:

## Style Preferences
<!-- Confirmed by user, not inferred -->

## Constraints
<!-- Physical, budget, regulatory -->
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High
Category
Prompt Injection
Content
- Windows: position, size cm

## Fixed Elements
<!-- Cannot move -->

## Current Furniture
<!-- Note if must stay -->
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Static analysis

No suspicious patterns detected.