ClawHub
Back to skill

Security audit

estate-settlement-navigator

Security checks for vulnerabilities and agentic risk

Overview

This skill is an offline estate-administration checklist and letter generator with no evidence of hidden execution, network access, persistence, or data exfiltration.

Safe to install for offline checklist and document-drafting help. Do not put real SSNs, account numbers, dates of birth, or other sensitive identifiers into shell commands or shared prompts; use placeholders, then add sensitive details directly to final documents in a controlled editor.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example command embeds highly sensitive personal data in plaintext, including a full name and a partially revealed SSN, without any warning to use placeholders or redact real identifiers. Because this skill is specifically intended for grieving users handling real estate matters, they are likely to copy the pattern directly into shells, chat transcripts, logs, screenshots, or support tickets, increasing the risk of privacy exposure and identity misuse.

Content

No source excerpt is available for this finding.