Security audit

Merge Drafts

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Markdown-only draft-merging skill, with minor wording and consistency issues but no evidence of hidden execution, persistence, credential access, or data exfiltration.

Before installing, be aware that the skill is primarily written for Chinese-language draft-merging workflows and may ask you to provide local files, URLs, or publicly viewable Feishu document links. Only share documents you intend the agent to read, and avoid changing private document permissions to public unless that is acceptable for your use case.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The "语言规范" section requires specific Chinese wording substitutions such as using "必须" instead of "try to" and "禁止" instead of "avoid". This imposes a language/locale policy on outputs without any user opt-in or explanation that the skill is limited to a Chinese-only or region-specific context.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The manifest description is written entirely in Chinese and provides no indication that other languages are supported or that this locale restriction is intentional. Under the policy, forcing a specific language without user choice or clear justification is a natural-language policy violation.

Intent-Code Divergence

Low

Confidence: 97% confidence
Finding: 步骤二明确写明“按6个维度打分”，但前文质量评估标准表仅列出5个维度（结构清晰度、信息完整度、表达质量、独特亮点、主题契合度）。这是文档内部对技能意图和执行规则的直接矛盾，会导致实现者或调用方对评分依据产生混淆。

Static analysis

No suspicious patterns detected.