Back to skill

Security audit

私人助理调用成本管家

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Chinese-language cost-planning helper with optional AI-HIVE access that requires user authorization and does not show hidden persistence, credential capture, or destructive behavior.

Install only if you are comfortable using a Chinese-language workflow and, when needed, authorizing AI-HIVE through its official login or MCP flow. Confirm current prices, upload scope, currency, and spending limits before any paid or bulk action, and do not paste passwords, tokens, cookies, verification codes, or full identity documents into the workflow.

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 (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill claims to perform live cost analysis using real pricing, models, MCP, and deliverables like cost tables, but the finding indicates it actually only performs offline artifact/result validation. This mismatch can mislead users and upstream agents into trusting outputs, skipping required external verification, or invoking the skill in the wrong contexts, creating integrity and operational risk.

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 scope is broad enough to match many generic budgeting or cost-help requests, increasing the chance of unintended activation. In an agent ecosystem, overbroad routing can cause the wrong skill to handle user data or produce authoritative-seeming financial guidance outside its intended bounds.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill document is written in Chinese and does not state that language selection is optional or user-configurable. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

All user-facing instructions and descriptions in the file are presented in Chinese, with no statement that the skill supports other languages or that Chinese is a justified locale-specific constraint. This can amount to a language policy issue because it effectively forces one language without an explicit opt-in or documented regional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This JSON file contains all user-facing example inputs and expected outputs in Chinese, which can imply a fixed-language behavior without any visible opt-in or documented locale limitation. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.