Back to skill

Security audit

证件与保养到期管家

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed reminder-and-expiry workflow with optional user-authorized AI-HIVE access and a local read-only result checker.

Before installing, be aware that using AI-HIVE is optional and can involve external authorization, uploads, or paid model calls. Keep the default draft-first workflow, do not paste passwords, tokens, cookies, verification codes, or full ID numbers into chat, and confirm budget and upload scope before any external use.

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 (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill's declared purpose is expiry/reminder management, but it also directs the agent to run an offline validation script and rely on result-contract artifacts unrelated to the user-facing reminder workflow. This hidden operational behavior expands the skill's effective scope and can mislead reviewers or downstream agents about what files are accessed and what actions are expected, increasing the risk of unintended file processing or misuse of validation logic.

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.