Security audit
Security checks for vulnerabilities and agentic risk
This Linear integration is not malicious, but it can make authenticated project-management changes without clearly requiring previews or user confirmation.
Install only if you are comfortable giving the agent a Linear API key and letting it send issue, project, and workflow data to Linear. Use a narrowly scoped or dedicated key where possible, avoid broad natural-language bulk requests, and require the agent to show the exact GraphQL request and affected Linear objects before any create, update, label, assignment, status, or cycle change.
The description says the skill is suitable for '需要linear api相关能力的开发场景' and repeats that it applies to '相关开发场景', which is vague and lacks clear trigger boundaries. This broad natural-language scope could overlap with many ordinary development requests involving project work, without specifying concrete invocation phrases or exclusion conditions.
The skill explicitly supports creating, updating, and bulk-operating on Linear issues, cycles, projects, and workflows, but it does not prominently require confirmation before making remote state changes. In an agent setting with exec access, this raises the risk of unintended or overbroad modifications to production project data through natural-language prompting.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### 运行环境
- **Agent 平台**: 支持 SKILL.md 的任意 AI Agent（Claude Code / Cursor / Codex / Gemini CLI 等）
- **操作系统**: Windows / macOS / Linux
- **网络**: 需可访问 Linear API（https://api.linear.app/graphql）
### 依赖项
| 依赖项 | 类型 | 是否必需 | 获取方式 |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### 运行环境
- **Agent 平台**: 支持 SKILL.md 的任意 AI Agent（Claude Code / Cursor / Codex / Gemini CLI 等）
- **操作系统**: Windows / macOS / Linux
- **网络**: 需可访问 Linear API（https://api.linear.app/graphql）
### 依赖项
| 依赖项 | 类型 | 是否必需 | 获取方式 |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### 运行环境
- **Agent 平台**: 支持 SKILL.md 的任意 AI Agent（Claude Code / Cursor / Codex / Gemini CLI 等）
- **操作系统**: Windows / macOS / Linux
- **网络**: 需可访问 Linear API（https://api.linear.app/graphql）
### 依赖项
| 依赖项 | 类型 | 是否必需 | 获取方式 |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### 运行环境
- **Agent 平台**: 支持 SKILL.md 的任意 AI Agent（Claude Code / Cursor / Codex / Gemini CLI 等）
- **操作系统**: Windows / macOS / Linux
- **网络**: 需可访问 Linear API（https://api.linear.app/graphql）
### 依赖项
| 依赖项 | 类型 | 是否必需 | 获取方式 |
The skill is explicitly classified as MD+EXEC and instructs the agent to execute curl commands against an external GraphQL endpoint using an API key. External transmission is expected for this integration, but it still creates real risk because prompts can induce outbound requests that expose project metadata or perform authenticated actions on a third-party service.
| curl | 命令行工具 | 必需 | 系统自带或安装，用于执行 GraphQL 请求 |
### 可用性分类
- **分类**: MD+EXEC（Markdown 指令驱动，需 exec 执行 curl 命令调用 GraphQL API）
- **说明**: 基于自然语言指令驱动 Agent 执行 Linear Issue 管理、Cycle 规划与查询
**API Key配置方式**:
This example shows an authenticated mutation to create an issue on a remote service. In the context of an agent with exec capability, demonstrating direct state-changing commands without built-in approval steps increases the likelihood of accidental or prompt-induced modification of external project data.
# 创建Issue
curl -X POST "https://api.linear.app/graphql" \
-H "Authorization: $PARAM" \
-H "Content-Type: application/json" \
-d '{
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -s -X POST "https://api.linear.app/graphql" \
-H "Authorization: $PARAM" \
-H "Content-Type: application/json" \
-d '{
The display name, summaries, and almost all instructional content are in Chinese, but the document does not state that Chinese is optional or provide an alternative language path. This can amount to a language policy issue when a skill effectively forces one language without user opt-in or a documented regional justification.
No suspicious patterns detected.