Security audit
Security checks for vulnerabilities and agentic risk
The skill is mainly an API code generator, but its requested write/exec authority and unclear runtime script instructions are broader than its stdout-only documentation suggests.
Install only if you are comfortable granting this skill command execution and file-write capability. Use it on a test project first, review generated auth/API code before using it, and only allow writes or redirects to paths you explicitly choose.
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
- `GET /users/:id` — 获取单个用户
- `POST /users` — 创建用户
- `PUT /users/:id` — 更新用户
- `DELETE /users/:id` — 删除用户
**说明**: 生成的代码含完整注释与错误处理,重定向到 `routes/user.js` 即可使用.
### 案例2: 生成产品 GraphQL Schema
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
- 创建订单测试（`POST /orders`）
- 获取订单列表测试（`GET /orders`）
- 更新订单测试（`PUT /orders/:id`）
- 删除订单测试（`DELETE /orders/:id`）
### 案例5: 生成速率限制器
**场景**: 开发者需要为 API 添加速率限制
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
- 创建订单测试(`POST /orders`)
- 获取订单列表测试(`GET /orders`)
- 更新订单测试(`PUT /orders/:id`)
- 删除订单测试(`DELETE /orders/:id`)
### 案例5: 生成速率限制器
**场景**: 开发者需要为 API 添加速率限制
The description says the skill should be used whenever the user needs API code generator related functionality, which is very broad and lacks concrete invocation boundaries. Although it notes unsuitability for complex needs, it does not provide specific trigger phrases or exclusion examples, increasing the risk of unintended activation for ordinary API discussions.
The description states '支持中文交互' and the file consistently presents the skill as Chinese-oriented, but it does not explicitly offer a language or locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.
The core feature text highlights Chinese interaction as a defining behavior, but does not mention that users may choose another language. This can be interpreted as a language constraint imposed by the skill rather than a user-selectable option.
The documentation states that generated code is only written to stdout, while the manifest explicitly grants the skill write capability. This mismatch can mislead users and orchestrators about the skill’s true side effects, increasing the chance of unintended file modification or overwrite if the implementation uses the declared write tool.
Phrases like '新API开发时触发', '接口文档需要时触发', and '前后端对接时触发' are broad situational descriptions rather than precise activation criteria. They do not clearly distinguish when this skill should activate versus when a general coding or documentation skill would be more appropriate.
The stated capability boundary says the skill does not automatically write files, but the skill is provisioned with write access. Even if the current workflow says users must redirect stdout manually, the extra capability broadens the attack surface and weakens user expectations about what the skill may do.