Back to skill

Security audit

Inheritance

Security checks for vulnerabilities and agentic risk

Overview

The skill has no code or persistence, but its inheritance/legal purpose is poorly aligned with generic tool-shopping instructions that could mislead users in a sensitive estate-planning context.

Review carefully before installing. This skill should not be relied on for legal, tax, inheritance, or estate-planning decisions unless it is rewritten with clear scope, jurisdiction limits, professional-advice disclaimers, and guidance to avoid sharing sensitive family or financial details with unrelated tools.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The user-facing description, headings, and example requests are entirely in Chinese, which implies a fixed language requirement for use. Under the policy, language constraints should either be optional for the user or clearly documented as region- or locale-specific; neither is stated here.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The heading and example prompts present the skill as a generic '财富传承' product/tool-usage assistant rather than a legal/advisory skill, directly contradicting the manifest. This kind of role confusion is dangerous because users may trust the skill for legal or estate matters while receiving irrelevant tool-discovery guidance, potentially causing disclosure of highly sensitive personal, family, or financial information in the wrong context.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill content is materially inconsistent with the declared purpose of inheritance and estate-planning consultation. Instead of domain-specific legal guidance, it describes generic tool-selection criteria, plugin support, storage, export permissions, and product-discovery behavior, which can mislead users into sharing sensitive estate or family data with unrelated tools or workflows. In a legal/wealth-transfer context, this mismatch increases the risk of inappropriate data handling and unsafe reliance on the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.