Security audit

111

Security checks for vulnerabilities and agentic risk

Overview

This is a small disclosed mock meeting-minutes skill with no hidden execution, network access, persistence, or sensitive data handling.

Before installing, treat this as a lightweight mock/template rather than a complete meeting-minutes automation skill. It appears low risk, but users should not expect real parsing or task automation unless the skill is further implemented.

A.I.G

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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: 声明描述的是一个具备明确会议纪要处理能力的技能，但实际代码只是一个没有任何功能实现的 Mock 入口文件，不包含会议纪要解析、任务细化、步骤拆解或最佳实践输出等行为。因此，代码实际行为与声明目的存在实质性不匹配。

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The description and usage scenario repeatedly describe the skill as applicable to any '会议纪要' related task and say it can automatically refine steps based on input and context, but they do not define specific trigger phrases, boundaries, or exclusion conditions. This broad wording could overlap with many ordinary requests about meeting notes and may cause unintended invocation.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: This Python file includes user-facing/comment natural-language content in Chinese (the module docstring and inline comment), which imposes a specific language/locale without any indication of user choice or documented regional justification. The policy for SQP-3 applies to all file types and flags language constraints that are not optional or explained.

Static analysis

No suspicious patterns detected.