Back to skill

Security audit

截图语音转待办助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, task-focused assistant for turning user-selected screenshots, audio, or notices into reviewable to-do/calendar artifacts, with reasonable safeguards around credentials, uploads, fees, and external actions.

Installers should be comfortable with a Chinese-language workflow and should only connect AI-HIVE or upload materials after confirming the exact selected files, tool schema, price, budget, and authorization scope. Do not provide passwords, tokens, verification codes, cookies, or broad personal archives to this skill.

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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

声明描述的是一个面向用户的内容处理与待办生成/导入工具,核心能力应包括从截图、语音、聊天或通知中提取信息并生成待办,可能还会调用外部工具或日历集成。实际代码却只是一个本地验证器:检查结果JSON中的skill_id、records、状态、action_kind、授权引用、evidence、execution_level、provider_task_id、domain字段状态,以及artifact路径和SHA-256哈希,并限制文件大小与目录穿越。代码注释还明确说明“never authenticates, calls APIs, or executes actions”。因此其主要目的与声明用途明显不一致,属于实质性描述—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.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description and primary instructions present the skill in Chinese only, which can impose a specific language on users without indicating that other languages are supported or that Chinese is optional. This matches the policy concern for language or locale constraints that are not presented as a user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire workflow is written as a Chinese-only operational specification and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.