此报告尚无所请求语言的翻译，当前显示规范英文报告。

版本化安全评估

报告编号: SA-480D7A74

7/5/2026, 4:13:52 PM

app-store-screenshots 安全评估 v3

Skill 安全认证报告

审计历史

审计模型: codex 历史报告

技能名称: app-store-screenshots
版本: v3
维护者: halt-catch-fire
来源: github.com/halt-catch-fire/skills/tree/main/guides/design/app-store-screenshots/
覆盖范围: 1 已扫描文件 · 271 分析行数
策略版本: 不可用

已确认问题摘要

未发现已确认的安全问题

已完成的审计没有记录已确认的安全问题，但这不证明该 Skill 没有副作用。

安装上下文

历史证据

本报告可能无法描述当前可安装的 artifact。请打开当前 Skill 详情页查看安装建议。

打开当前 Skill 详情页

本报告不会阻止或授权 manifest 或 ZIP。

Several static detections are real low-to-medium risks because the skill asks users to install and run the third-party belt CLI. The remaining detections are Markdown fences, diagrams, or metadata false positives; no prompt injection or covert exfiltration intent was found.

报告位置

历史报告

使用本报告安装前，请先查看审计历史。

审计证明

无法签发证明

所需的不可变绑定不完整。

人工验证

未进行人工验证

本报告没有人工验证记录。

覆盖范围

1 已扫描文件 · 271 分析行数

有 11 项内容需要查看

局限

本报告不声称进行了运行时或沙箱执行，也不证明不存在副作用。

证据链

证据从来源绑定延伸到安装契约。证据可用于验证，但不是安全保证。

来源

绑定不可用
构件

身份信息不完整
审计

已完成
安装契约

打开 manifest 进行验证
打开 manifest

观察到的能力

“已观察到”表示本报告记录了支持证据；“未记录”不证明该能力不存在。

包含脚本

可能执行 Skill 随附的代码。

本次审计未记录

网络访问

可能连接外部服务。

在 2 个证据位置观察到

文件系统访问

可能读取或写入本地文件。

本次审计未记录

环境变量

可能读取进程环境中的值。

本次审计未记录

外部命令

可能调用 Skill 之外的命令或程序。

在 20 个证据位置观察到

能力复核项 (11)

中

SKILL.md:7

Ruby/shell backtick execution

> **Install the belt CLI skill:** `npx skills add belt-sh/cli`

The inline command asks users to run npx skills add belt-sh/cli, which installs an external skill through a package runner. It is not automatic execution, but it creates a real supply-chain risk if followed.

中

SKILL.md:17-26

Ruby/shell backtick execution

```bash

The quick-start bash block instructs belt login and belt app run, which launch a third-party CLI and remote model call. The command family is constrained, but it still executes external tooling.

中

SKILL.md:137-144

Ruby/shell backtick execution

```bash

The fenced bash example runs belt app run against a remote image model. It is legitimate screenshot generation, but it executes a third-party CLI and sends prompt data externally.

中

SKILL.md:148-154

Ruby/shell backtick execution

```bash

The fenced bash example calls belt app run for a remote image generation model. The usage is documented and bounded, but it still depends on external CLI execution.

中

SKILL.md:158-165

Ruby/shell backtick execution

```bash

The example runs belt app run to generate a lifestyle mockup through a remote service. It is expected behavior, but it can disclose prompt content to third parties.

中

SKILL.md:169-175

Ruby/shell backtick execution

```bash

The bash example runs belt app run infsh/stitch-images with local image filenames. This can upload or process local screenshot assets through an external CLI.

中

SKILL.md:206-211

Ruby/shell backtick execution

```bash

The preview video example runs belt app run against a remote video generation model. This is legitimate for the skill, but it executes external tooling and transmits prompt data.

中

SKILL.md:262-267

Ruby/shell backtick execution

```bash

The related skills block recommends npx skills add commands for external skill installation. These are manual commands, but they introduce supply-chain risk if executed.

中

SKILL.md:267-269

Ruby/shell backtick execution

```

The section includes a belt app store command after the fenced block. It is a documented CLI action, not automatic execution, but it invokes third-party tooling.

低

SKILL.md:11

Hardcoded URL

Create app store screenshots and preview videos via [inference.sh](https://inference.sh) CLI.

The skill explicitly depends on the inference.sh network service for screenshot and video generation. This is expected, but users should know prompt and asset data may leave their environment.

低

SKILL.md:15

Hardcoded URL

> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer

The install instructions use a raw GitHub URL from an external repository. It is a normal documentation link, but it is still a third-party network dependency.

风险问题

已确认的安全问题与仍需审核的项目分开展示。

此次已完成的审计未记录已确认的安全发现。

补救措施

本次审计记录了建议的修复措施。实施这些措施是维护者的责任。

FIX-001
中
External CLI execution and related skill installs

Require explicit user review before running belt or npx skills add commands, and pin trusted install sources where possible.
FIX-002
低
Remote inference data disclosure

Add a clear privacy note that prompts, screenshots, and generated assets may be sent to inference.sh or model providers.

专家证据

不可变主体身份、扫描器元数据、已排除匹配项和源码级证据。

Artifact 主体

Marketplace 提交: 不可用
内容哈希: 不可用
目录树哈希: 不可用
Skill 路径: 不可用
审计载荷哈希: 不可用

分析元数据

审计模型: codex

分析状态: 已完成

范围仅限于已记录的文件、行数、方法和证据；本报告不声称进行了运行时或沙箱执行。

验证与导出

JSON 报告 CITATION.cff SARIF 2.1.0 已签名安装清单

manifest 和 lockfile 将安装 artifact 绑定到加密哈希。该完整性声明独立于安全评估。

审计证明: not_attestable