Back to skill

Security audit

老板异常事项提醒助手

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Chinese-language workflow for turning business ledgers and thresholds into reviewable exception reports, with optional AI-HIVE use gated by user login, scope, and cost approval.

Install only if you are comfortable using a Chinese-language workflow and, when AI-HIVE is used, authorizing that service in a browser and approving exactly which business data and budget may be used. Do not paste passwords, tokens, verification codes, or cookies into the chat.

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 (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

声明描述的是一个面向经营异常提醒与例外管理的业务助手,核心能力应是汇总经营数据、识别异常、形成看板和责任分派,可能还涉及通知偏好与工具联动。给出的代码却只是一个本地离线校验器,主要验证结果记录是否符合预定义输出契约,以及artifact文件哈希和路径是否合法。它明确不认证、不调用API、不执行动作,也没有任何异常识别、提醒生成、通知发送、看板构建、AI模型调用或MCP交互逻辑。因此代码的主要目的与声明用途明显不一致,属于实质性描述-行为不匹配。

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
94% confidence
Finding

The description says the skill applies when the user needs '只提醒重要的事' and '老板例外管理', and line 8 repeats '适用于只提醒重要的事等需求'. These phrases are broad and conversational, with no explicit trigger list, exclusions, or narrow invocation context, so they could overlap with ordinary requests and cause unintended activation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The display name, short description, and default prompt are all written to require operation in Chinese, and the prompt does not indicate any option to use another language. This can violate language/locale policy when a skill imposes a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The natural-language instructions throughout the file require Chinese proficiency, but the skill does not state that Chinese is optional, user-selected, or required for a specific regional/compliance context. This can violate a language/locale policy that expects skills to avoid forcing a specific language without opt-in.

Content

No source excerpt is available for this finding.