Security audit

工作邮件起草

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese-language helper for drafting or rewriting work emails and long business messages, with no code execution, external access, persistence, or hidden behavior.

Install this if you want a Chinese work-email drafting assistant. Review generated drafts before sending, especially for legal, salary, disciplinary, contractual, or customer-facing commitments, because the skill is designed to draft text rather than verify facts or send messages for you.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (2)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The description uses broad natural-language triggers such as '写邮件、回这封信、帮我措辞', which are common everyday phrases and can cause the skill to be invoked when the user did not explicitly intend this specific capability. In an agent environment, overbroad routing can expose user message content to the wrong skill, produce unintended actions or drafts, and interfere with safer or more appropriate skill selection.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: The instruction '默认中文' sets Chinese as the default output language without explicit user selection, which can cause unintended language handling when the user context or source email is in another language. While not a direct security flaw, it can lead to miscommunication, accidental disclosure through mistranslation, or unsafe assumptions in business correspondence workflows.

Static analysis

No suspicious patterns detected.