Back to skill

Security audit

预约电话准备与跟进助手

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Chinese-language appointment-call preparation workflow with optional user-authorized AI-HIVE/MCP use and an offline result checker, not an automatic hidden calling or account-control tool.

Install this only if you want a Chinese-language appointment-call preparation workflow. Before using AI-HIVE or any phone/payment/upload capability, confirm the service, data scope, price, budget, and authorization; do not provide passwords, verification codes, tokens, cookies, or full identity documents in 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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill advertises appointment-call preparation and possible tool-assisted execution, but the analyzed behavior appears limited to offline validation of existing result files. This mismatch can mislead operators or downstream agents into assuming business actions were performed or are supported, creating integrity and auditability risks around real-world scheduling, user authorization, and task completion.

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.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file presents all user-facing policy and usage guidance in Chinese, but it does not state that the skill is China-specific or offer an opt-in choice of language. That can violate language/locale policy because it forces a specific language experience without documented user selection or justification.

Content

No source excerpt is available for this finding.