Security audit

05 Monthly Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese monthly compliance report template that asks the user for relevant business data but does not install code, persist settings, run commands, or transmit data.

Install only if this reporting workflow matches your organization. Before pasting data, remove unnecessary personal identifiers, privileged legal details, and confidential case text unless your approved internal process allows that information in the agent environment.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: L032-L034 仅写明“每月末（或管理层需要时），用户提供月度数据，生成完整月报”。其中“管理层需要时”边界非常模糊，未限定具体触发短语、输入格式或排除场景，容易与一般性的“生成报告/汇总数据”请求重叠。

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill explicitly asks users to provide complaints, risk events, supplier ratings, and litigation/regulatory matters, all of which can contain sensitive business, personal, or legally privileged data. Because it gives no warning about minimization, masking, or approved handling channels, users may paste raw confidential records into the system, creating material privacy, confidentiality, and compliance exposure.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: 文件从名称、作者到正文均默认该技能以中文并以“阿里巴巴内控部”的固定组织身份运行，但未说明是否允许用户选择其他语言或适用范围。若组织政策要求语言/地区选择应由用户决定，这种默认强制单一语言/身份表述可能构成自然语言层面的政策不合规。

Static analysis

No suspicious patterns detected.