Back to skill

Security audit

Guardianship Supervision and Asset Oversight Advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill provides guardianship planning checklists, with a privacy caution about sharing sensitive family documents.

Share a minimal, de-identified summary first. Redact names, identification and account numbers, signatures, and unrelated medical or third-party details from necessary excerpts, and share only information you are authorized to disclose. Check your AI service's privacy settings and have qualified professionals review consequential arrangements. All six artifact files were inspected; the scanner reported complete coverage without material gaps.

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
  • 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 skill requests complete supporting materials without a privacy warning or redaction guidance.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The FAQ asks users to provide complete factual materials, including amounts and original contracts or supporting records, without advising minimization or redaction. In a guardianship context, those documents may expose a vulnerable person's identity, financial accounts, medical information, and third-party personal data unnecessarily to the AI service. The planning-only scope and professional-review disclaimers do not address this privacy risk, although no external transmission destination or malicious collection mechanism is specified.

Content

No source excerpt is available for this finding.