ClawHub
Back to skill

Security audit

Homestruk Tenant Screening

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent tenant-screening guidance skill with one privacy-sensitive local draft-save instruction users should handle carefully.

Before installing, treat generated tenant-screening letters as sensitive applicant records: confirm before saving, avoid unnecessary PII in filenames, store drafts in an access-controlled location, delete records when no longer needed, and verify all screening criteria with current Massachusetts and federal housing law.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The 'When to Use This Skill' section lists triggers like 'Should I approve this tenant?' and 'What are my screening criteria?' without narrowing the context of invocation or providing exclusion conditions. These phrases are common in everyday landlord discussions and could cause unintended activation because the skill does not define specific trigger boundaries or negative examples.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
Saving a rejection letter draft to a user path without warning about disk writes or applicant data handling can expose PII, financial screening details, and adverse-action information. In this skill's context, the generated document likely includes regulated applicant information, so silent or default persistence materially increases privacy, compliance, and data leakage risk.

Context-Inappropriate Capability

Low
Confidence
93% confidence
Finding
The skill explicitly directs saving a rejection letter containing applicant-identifying and potentially sensitive screening information to a local workspace path. That adds filesystem write behavior to a screening skill and can create unnecessary persistence of personal data, increasing exposure from accidental disclosure, over-retention, or access by other tools/users on the same system.

Static analysis

No suspicious patterns detected.