Security audit

codebase-to-course-cn

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a legitimate codebase-to-course generator, with expected file creation and a small local build step that are disclosed and aligned with its purpose.

Install if you want an agent to read a codebase and generate a local HTML course. Use it on repositories you trust or in a disposable workspace, check the derived output directory before generation, and review generated HTML before sharing or opening it for sensitive codebases.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (2)

Context-Inappropriate Capability

Medium

Confidence: 93% confidence
Finding: 技能目标本质是分析代码库并生成课程内容，但却进一步要求执行 `bash build.sh` 并在浏览器中打开结果，这引入了不必要的命令执行和本地应用启动面。若参考文件或生成内容被污染，构建脚本可能执行任意 shell 操作，浏览器打开本地生成页面也可能触发主动内容执行或隐私暴露。

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: 文档要求在用户提供 GitHub 链接时执行 `git clone`，并在后续写入课程目录、运行 `bash build.sh`，但没有要求在这些副作用操作前进行明确告知和确认。用户可能只期望获得分析结果，却在不知情下触发本地文件修改、远程内容拉取和 shell 执行，造成工作区污染、脚本风险或供应链暴露。

Static analysis

No suspicious patterns detected.