Security audit

OPC 商业模式画布

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed business-model worksheet that may save a user-confirmed local Markdown report, with no code execution, network access, or hidden persistence found.

Install only if you want a Chinese-language OPC business model canvas assistant. Before exporting, choose the file path deliberately and review whether the report includes private income goals, resources, contacts, or business plans you do not want saved locally.

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 (6)

Vague Triggers

Medium

Confidence: 97% confidence
Finding: The trigger phrase “商业模式” is extremely broad and likely to activate during ordinary discussion unrelated to this specific skill. Over-broad activation can cause unintended collection of user business details and push the assistant into file-writing behavior when the user did not intend to invoke this skill.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The phrase “帮我建模” is ambiguous and can refer to many forms of modeling, not specifically OPC business canvas analysis. This increases the risk of accidental activation, causing the assistant to ask for personal or commercial information under the wrong context.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: “商业画布” is also a broad phrase that may occur in generic entrepreneurship discussions. In this skill, broad triggers are more concerning because activation leads to structured elicitation of user data and possible persistence of that data to disk.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill instructs writing a Markdown report containing user-supplied personal and business information to a file, but it does not require a clear privacy notice, overwrite warning, or confirmation of exactly what data will be stored. This can lead to unintended persistence of sensitive information and accidental overwriting of existing files.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: All user-facing instructions, triggers, and output expectations are specified in Chinese, which can amount to forcing a single language without opt-in. The file does not state that the skill is region-specific or give users an option to choose another language.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: This manifest presents the skill name and description in Chinese while the default prompt is fixed in English. That creates a language-policy concern because the skill appears to impose or assume a language mode without any user opt-in or documented choice.

Static analysis

No suspicious patterns detected.