Back to skill

Security audit

个人与公司记忆隔离助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed privacy-boundary workflow with an optional local validator and user-controlled AI-HIVE connection steps.

Before installing, be aware this workflow may process sensitive personal and company boundary information. Use it with minimal necessary inputs, do not paste passwords or tokens, and only connect AI-HIVE or upload files after confirming the scope, cost, and authorization in the official flow.

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
98% confidence
Finding

The declared description presents a helper for separating personal and corporate memory/context and producing specific governance artifacts. The supplied code instead performs schema/invariant validation on an already-produced result file, including status/action consistency checks, provenance requirements, artifact hash verification, relative-path safety checks, and simple secret-pattern detection. These behaviors are materially different from the declared purpose. While the code is benign and offline-only, its primary purpose is result-record validation rather than memory isolation or artifact generation as described.

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.