Security audit

教案设计器

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese-language lesson-planning skill with disclosed templates and privacy guardrails, and I found no hidden execution, credential use, or unsafe data handling.

Installers should understand this skill is intended for Chinese-language teaching workflows. When using it with student-learning summaries, provide only de-identified or aggregate data and review any generated lesson plan before using it in class.

SkillSpector

By NVIDIA

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 (4)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The manifest description says to activate the skill when a teacher says phrases like "帮我设计一节课", "写一份教案", and "这节课怎么上", which are broad natural requests that could match many routine conversations. The file does not provide exclusion conditions or tighter scope boundaries to distinguish when this specific skill should activate versus other teaching-assistant skills.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The "触发时机" table lists broad scenarios like "写一份教案", "帮我安排一节期末复习课", and "我们组下周要集体备课，出一份示范教案" as triggers, but it does not clearly define required inputs, scope limits, or when another skill should be preferred. Because the examples are scenario-based rather than constrained activation rules, unintended invocation overlap is likely.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: This markdown file contains natural-language content exclusively in Chinese and does not indicate that users may choose another language or that the template is intentionally limited to a Chinese-language context. Under the policy rule for language or locale constraints, a forced language without opt-in can be a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: This markdown file presents all instructions, templates, and usage guidance exclusively in Chinese. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.