Back to skill

Security audit

活动聚会筹备与报名助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed event-planning assistant with optional AI-HIVE/MCP use that requires user authorization before uploads, paid actions, messaging, ticketing, or other external changes.

Install only if you are comfortable using a Chinese-language event-planning workflow that may optionally connect to AI-HIVE. Before using external tools, verify the AI-HIVE domain, current tool list, upload scope, pricing, budget limit, and whether any message, payment, ticketing, deletion, or system write has been explicitly authorized.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

声明描述的是一个面向最终用户的活动筹备与报名辅助能力,但代码实际仅实现了一个本地验证器。它不会生成活动计划、管理参与者、处理票务、发送提醒,也没有任何与聚会场景相关的业务逻辑。相反,代码的核心功能是对结果记录进行结构与一致性校验,并验证本地artifact文件的哈希和路径安全性。这属于审计/验证工具,与声明的主要用途存在实质性不符。

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
86% confidence
Finding

L03 将触发条件描述为“在用户需要聚会管家、活动私人助理、报名提醒、票务助手时”,这些表述较宽泛,缺少明确的触发短语、边界或排除条件。对于清单型技能清单/描述文件,这种宽泛描述可能让路由器或调用方在普通活动咨询场景下也错误匹配该技能。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
65% confidence
Finding

整个技能说明文件均以中文编写,且未见任何允许根据用户偏好切换语言、或声明仅面向特定中文用户群体的说明。按规则,若技能实际上强制特定语言而没有用户选择或明确限定区域/受众,可能构成自然语言层面的语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill’s invocation text is broad and underspecified: it tells the model to use the skill whenever the user provides materials for an event-planning task, but does not define strict trigger boundaries, required prerequisites, or disallowed use cases. In an agent environment, this can cause over-invocation, misrouting, or unsafe delegation to tools/permissions/paid capabilities without sufficient user intent verification, especially because the description explicitly mentions connecting to verification tools, permissions, and fees.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file contains user-facing natural-language content exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without user opt-in is a policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

L08 写明“适用于聚会管家等需求”,其中“等需求”属于开放式、模糊范围,没有给出完整触发列表或不适用情形。对于 markdown 技能说明,这会削弱调用边界,增加被泛化到相邻任务的可能性。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The note is written entirely in Chinese and provides the only user-facing instruction in the file. Because the file does not offer an alternate language or indicate that the skill is intentionally limited to Chinese-speaking users, this creates a locale-policy concern under the language-choice rule.

Content

No source excerpt is available for this finding.