Back to skill

Security audit

HOA Nightmare Navigator

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign, with medium confidence, while flagging concerns about its HOA fine guidance, meeting recording advice, and undeclared network capability.

Before installing, consider whether you are comfortable relying on preliminary HOA guidance that the scanner says may misstate fine requirements. Check local recording laws and meeting rules before recording, and treat any fine-check result as something to verify. Skillspector's analysis was partial: 4 of 5 components were scanned, and one static check on SKILL.md was limited by a parser span limit.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The escalation workflow calls for recording an open-forum statement without warning about recording consent or meeting rules.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow recommends recording an open-forum statement without checking applicable recording law, consent requirements, or association meeting rules. In a contentious HOA dispute, following this advice could capture other participants without required consent and expose the user to privacy complaints, legal liability, or meeting sanctions; recording is not necessarily prohibited in every jurisdiction.

Content

No source excerpt is available for this finding.

The advertised state-specific statutory fine-cap check is implemented as state-independent heuristics.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The fine-review logic applies the same $150 first-offense and $1,000 repeat-fine heuristics regardless of jurisdiction; selecting a state changes descriptive text, not the checks. Its categorical verdict can misrepresent a preliminary heuristic as a statutory compliance assessment, causing users to challenge valid fines or accept invalid ones in consequential housing disputes.

Content

No source excerpt is available for this finding.