Back to skill

Security audit

Real Estate Engine

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a real estate template, but its tenant-screening workflow could affect housing eligibility using sensitive personal data without enough built-in compliance guardrails.

Review this skill carefully before installing if you plan to use the tenant-screening features. Do not enter unnecessary applicant personal data, and do not use the output as the sole basis for accepting or denying housing. Tenant screening should be handled with documented lawful criteria, required consent, jurisdiction-specific legal review, and compliance with Fair Housing, consumer-reporting, privacy, and local criminal-history or eviction-record rules.

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)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The tenant-screening section instructs users to evaluate criminal history, eviction records, sex-offender status, income, and creditworthiness, but it does not prominently warn that these checks involve sensitive personal data and are subject to fair-housing, privacy, consumer-reporting, and anti-discrimination laws. Because the skill provides disqualification criteria and scoring guidance, a user could rely on it to make legally significant housing decisions in a way that produces unlawful or biased outcomes.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The command "Screen this tenant" invites users to submit applicant information for automated evaluation without any immediate warning that the input may include highly sensitive personal data and that the output could materially affect housing eligibility. In this context, the command operationalizes the earlier screening framework, making it easy to use the skill for consequential decisions without adequate legal, privacy, or anti-bias safeguards.

Static analysis

No suspicious patterns detected.