Back to skill

Security audit

家庭补货采购清单助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed household restocking assistant with optional, user-authorized AI-HIVE access and no evidence of hidden persistence, credential theft, or automatic purchasing.

Before installing, confirm you are comfortable with a Chinese-language household shopping workflow and optional AI-HIVE/MCP use. Do not provide passwords, tokens, cookies, verification codes, or full identity documents; approve any uploads, paid model calls, orders, payments, or external changes only after reviewing the stated scope and cost.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose is a household restocking assistant, but the referenced behavior includes offline validation, path-safety checks, hash verification, and credential-pattern detection in saved records. This hidden or undocumented auxiliary behavior expands the effective capability of the skill and can mislead users and operators about what files are inspected and what data is processed, increasing the risk of unintended local data access or over-collection.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

L03 将触发场景描述为“家庭采购助手、买菜助手、自动补货、购物管家时”,其中“买菜助手”“购物管家”这类表述较宽泛,可能覆盖大量普通对话场景,且没有明确列出触发边界或排除条件。该描述缺少更具体的调用约束,容易导致技能在非预期的日常购物相关对话中被唤起。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

L08 使用“适用于家庭采购助手等需求”来描述适用范围,但“等需求”表述模糊,没有说明哪些相邻需求不应触发该技能。对于 markdown 技能说明,这种开放式范围会使调用条件不清晰,增加误触发风险。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The display name, description, and default prompt are entirely in Chinese, which indicates a fixed language choice in the skill's natural-language interface. There is no indication that the user can choose another language or that the locale restriction is intentionally documented for a region-specific use case.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The default activation prompt is broadly phrased and can trigger the skill whenever a user provides materials related to household restocking, without clear boundaries on when the skill should or should not activate. In a tool-using procurement workflow, overbroad activation increases the chance of inappropriate invocation, unnecessary data collection, or unintended tool/expense usage before the user has explicitly confirmed scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file presents all user-facing policy and operational guidance exclusively in Chinese. Under the language/locale policy rule, forcing a specific language without offering the user a choice or documenting a justified locale constraint is a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language note is written only in Chinese, which can impose a language expectation on users without opt-in or alternative locale support. Under the policy rule for language or locale constraints, this is a potential violation because no user choice or justification is provided in the file.

Content

No source excerpt is available for this finding.