ClawHub
Back to skill

Security audit

Rental

Security checks for vulnerabilities and agentic risk

Overview

This is a rental-advice skill made of Markdown guidance; it has some privacy and legal-safety caveats but no hidden execution, persistence, or data access behavior.

Reasonable to install for rental help, but treat legal, credit/background screening, and access-code guidance as prompts to verify local rules and use secure channels. Do not share applicant documents, Wi-Fi passwords, lockbox codes, or full addresses more broadly than necessary.

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
  • 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 (3)

Hidden Instructions

High
Category
Prompt Injection
Content
## Session State

<!-- active_role: tenant | landlord | host | guest | equipment -->
<!-- current_search: location, budget, requirements -->
<!-- properties: addresses being tracked -->
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The tenant-screening section instructs landlords to collect and evaluate highly sensitive personal data, including government ID, income, credit, background, landlord references, and employment information, but it does not mention obtaining applicant consent, complying with screening and privacy laws, securing the data, limiting retention, or avoiding discriminatory use. In a rental skill, this omission can lead users to perform unlawful or unsafe screening practices that expose applicants to privacy harm, misuse of personal information, and legal violations.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The templates encourage sharing sensitive operational details such as a full address, entry/access instructions, Wi‑Fi credentials, and a phone number in generic message text without any guidance on limiting disclosure to confirmed guests or using platform-protected channels. If copied into unsafe contexts, this can enable unauthorized access, privacy violations, social engineering, or compromise of the property network.

Static analysis

No suspicious patterns detected.