Back to skill

Security audit

Home Renovation

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed local home-renovation planner that stores project notes, budgets, timelines, and contractor details in a dedicated folder.

Before installing, understand that this skill is meant to keep renovation records across sessions, including budgets and contractor contact details, in ~/home-renovation/. Choose the on-request or declined integration preference if you do not want it to engage whenever renovation topics come up.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · memory-template.md (reported line 15)May include surrounding context.

md
integration: pending

## Active Projects
<!-- List current renovation projects -->
<!-- Example: Kitchen remodel - started Jan 2026, budget $40K -->

## Context

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · memory-template.md (reported line 19)May include surrounding context.

md
<!-- Example: Kitchen remodel - started Jan 2026, budget $40K -->

## Context
<!-- What you've learned about their situation -->
<!-- Their home type, location (for cost context), experience level -->

## Notes

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The integration setting 'always' paired with 'Activate whenever renovation mentioned' creates an overly broad trigger that can cause the skill to engage and retain context from ordinary conversation without a clear, specific user request. In a memory-enabled skill, this can lead to unintended activation, unnecessary profiling of user interests, and collection of project details the user did not expect to be tracked.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction to read this setup when the directory doesn't exist or is empty, combined with 'Start the conversation naturally' and later guidance to engage early, creates an ambiguous activation boundary. This can cause the skill to begin participating without a clear user request, increasing the chance of unintended behavior, surprise persistence, or inappropriate context switching.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to save project details, preferences, contractor information, and budgets to local files under ~/home-renovation/ without requiring a clear user-facing disclosure or consent flow. Persistent storage of potentially sensitive household and financial information without notice can violate user expectations and expose private data to other local processes, users, or future sessions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.