Back to skill

Security audit

客户跟进私人销售助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed sales follow-up drafting skill with cautious handling of customer data and optional external AI-HIVE/CRM use, not a hidden automation or persistence mechanism.

Install this only if you intend to use it for authorized sales follow-up work. Before using AI-HIVE or CRM connectors, confirm what customer data may be uploaded, keep credentials out of chat, review drafts before any outreach, and require explicit approval for sending messages or changing business systems.

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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

声明描述的是一个销售跟进助手,应围绕客户记录生成销售跟进台账、话术草稿和待审批动作,并可能借助AI-HIVE/MCP及实际工具完成销售辅助流程。但代码并未处理客户信息、沟通记录、销售话术、CSV生成或任何销售工作流,也没有调用模型或MCP。相反,它只是一个通用的离线校验器,验证JSON结果与本地工件的结构/来源约束,且注释中明确说明不会认证、调用API或执行动作。因此其主要目的与实际行为与声明严重不符,属于明显描述-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
91% confidence
Finding

The trigger wording is broad enough to overlap with common business-assistant requests, which can cause the skill to activate in contexts the user did not intend. Because this skill handles customer records, outreach drafting, and possible external integrations, mis-triggering could expose sensitive business data to unnecessary processing or initiate unwanted follow-up planning.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This file contains user-facing operational instructions exclusively in Chinese, which effectively imposes a language choice on users. Under the policy, locale or language constraints should either be optional, user-selected, or clearly justified as region-specific.

Content

No source excerpt is available for this finding.