Security audit

Content Structure Designer

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language writing-structure helper with no code execution, network access, credential use, persistence, or hidden high-impact behavior.

Install this if you want a Chinese-language assistant for article outlines and content templates. Be aware it may activate on broad writing-help requests, so users who prefer another language or narrower routing may want the publisher to document language preference and tighten triggers.

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 (3)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The README presents the skill's purpose and usage only in Chinese, which can amount to forcing a specific language on users without offering an alternative or opt-in. The policy specifically calls for flagging language or locale constraints unless user choice or justification is documented.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger phrases are broad, generic writing-help terms such as '不知道怎么写' and '如何组织内容', which are likely to match many normal user requests outside the intended scope. This can cause the skill to activate unexpectedly and steer unrelated conversations into its workflow, creating prompt-routing interference and reducing the safety and predictability of the agent.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The entire skill instruction set is presented in Chinese and does not indicate that users may choose another language. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is documented and justified.

Static analysis

No suspicious patterns detected.