ClawHub
Back to skill

Security audit

rental-property-sell-or-hold

Security checks for vulnerabilities and agentic risk

Overview

This skill provides rental-property decision analysis using owner-supplied figures, with explicit privacy safeguards and no authority to execute financial transactions.

Share only necessary financial details and keep the resulting document private. Verify calculations, assumptions, and tax treatment with qualified advisers before acting on recommendations.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

The trigger list includes broad terms such as “cash flow,” “condo,” “property tax,” “ETF,” and “concentration” that can activate the skill outside rental-property sell-or-hold decisions.

Medium
Category
Trigger Abuse
Confidence
93% confidence
Finding

These standalone terms also occur in budgeting, homeownership, general investing, and unrelated discussions. Although the preceding description establishes a sell-or-hold purpose, the explicit trigger list does not require that context or exclude other uses of these terms.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.