📦
remotion-render
38从 React 代码渲染 Remotion 视频
团队需要可重复的视频渲染，而不必管理本地 Remotion 流程。此技能会将 React/Remotion 组件发送到 inference.sh，并返回 MP4。
设计与创意 查看
技能 agent-tools
📦
agent-tools
内容修订 r1 严重 🌐 网络访问🔑 环境变量📁 文件系统访问⚙️ 外部命令
从 CLI 运行 AI 应用
团队需要一种一致的方式来调用多个 AI 服务，而无需自定义集成。此技能会指导 Claude、Codex 和 Claude Code 使用 inference.sh CLI 进行发现、执行和任务跟踪。
支持: Claude Codex Code(CC)
请勿自动安装此 Skill。
权威策略要求在执行任何安装操作前由操作人员审查。
使用我的智能体安装
将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。
智能体请求
Review the Skillstore skill "agent-tools" from https://skillstore.io/skills/inference-sh-6-agent-tools.md and its manifest at https://skillstore.io/api/skills/inference-sh-6-agent-tools/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.你的智能体仍应展示其计划，并按安全策略请求必要确认。
Agent 可读资源
当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。
测试它
正在使用“agent-tools”。 查找可以生成简短产品视频的应用。
预期结果:
相关视频应用的排序列表、关键提供商名称、预期输入字段以及推荐的首次测试。
正在使用“agent-tools”。 运行图像生成提示词并跟踪完成情况。
预期结果:
助手会选择一个应用、提交作业、报告任务 ID，并在准备就绪时总结输出 URL。
正在使用“agent-tools”。 准备安全的 Twitter/X 发帖工作流。
预期结果:
助手会识别所需的 X 应用、请求确认，并在运行前说明账户操作。
安全审计
严重v4 • 2026/7/5 打开版本化报告
The skill is transparent about using the inference.sh CLI, but several install instructions use curl-to-shell and remote binary installation patterns. Most API-key and documentation-link findings are false positives, while external CLI execution, hosted-app data transfer, and Twitter/X automation remain real risks.
5
已扫描文件
554
分析行数
22
复核项
0
已忽略误报
已确认安全问题 (6)
严重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The command pipes a remotely downloaded installer directly into sh. This can execute changed or compromised remote content without local inspection.
严重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The reinstall example repeats the curl-to-shell pattern. It allows remote script content to execute immediately on the user machine.
严重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The installation example pipes a remote script directly to sh. That is a recognized high-risk install pattern even when the domain is expected.
严重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The primary install instruction executes remote shell content with sh. This is a critical supply-chain risk if the endpoint or transport is compromised.
高
Public Social Media Automation Capability
The skill includes examples for x/post-tweet and lists Twitter/X actions such as posting, direct messages, follows, likes, and retweets. These actions can affect a public account when run with authenticated credentials.
The cited lines explicitly show x/post-tweet and Twitter/X automation commands. Misuse depends on credentials, but the business action is clear.
中
User Data Sent to Hosted Third-Party Apps
The skill routes prompts and input files to hosted apps such as image, video, LLM, search, and 3D services through infsh app run. This can expose user content to the selected app provider.
The examples show remote app execution with prompts, and the references state that outputs are returned through cloud URLs. The behavior is intended but privacy-relevant.
能力复核项 (22)
这些是真实的本地能力，对此技能可能是预期行为，因此需要复核，但不会按已确认恶意行为计分。
高
Shell command substitution
> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep
The command uses nested shell substitution with a remote manifest to build a download URL. A changed manifest can influence what binary is downloaded.
高
Hidden file in home directory
> mv inferencesh-cli-* ~/.local/bin/inferencesh
The manual install command moves a downloaded executable into ~/.local/bin. That is a normal user install path, but it places remote code in PATH.
中
Ruby/shell backtick execution
> ```bash
The referenced manual install block contains shell commands that download, verify, extract, and install a remote binary. It is documented setup, but it still executes external commands on the user system.
中
Ruby/shell backtick execution
```bash
The quick examples contain infsh app run commands that send prompts to hosted AI apps. This is intended behavior, but it is real external command execution.
中
Ruby/shell backtick execution
| List all apps | `infsh app list` |
The command invokes infsh to list remote apps. It is expected read-only behavior, but it still runs an external CLI against a network service.
中
Ruby/shell backtick execution
| Search apps | `infsh app list --search "flux"` |
The command invokes infsh search against the hosted app catalog. It is a legitimate command, but it is external CLI activity.
中
Ruby/shell backtick execution
| Filter by category | `infsh app list --category image` |
The category filter runs infsh against the remote app catalog. This is intended but still an external command path.
中
Ruby/shell backtick execution
| Get app details | `infsh app get google/veo-3-1-fast` |
The command retrieves remote app details through infsh. It is normal discovery behavior, but it depends on external CLI execution.
中
Ruby/shell backtick execution
| Generate sample input | `infsh app sample google/veo-3-1-fast --save input.json` |
The command generates and saves a sample input file through infsh. It combines external CLI use with a local file write.
中
Ruby/shell backtick execution
| Run app | `infsh app run google/veo-3-1-fast --input input.json` |
The command runs a hosted AI app with local input. It can transmit user-provided data to a remote service.
中
Ruby/shell backtick execution
| Run without waiting | `infsh app run <app> --input input.json --no-wait` |
The no-wait run command submits remote work and returns before completion. It can transmit data and leave asynchronous jobs running.
中
Ruby/shell backtick execution
| Check task status | `infsh task get <task-id>` |
The task status command calls the remote inference.sh service. It is expected behavior, but it is still external command execution.
中
Ruby/shell backtick execution
```bash
The related-skills block uses npx skills add commands to install additional skills. Installing more community capabilities expands the execution surface.
中
Template literal with command substitution
> ```bash
The manual install block includes shell substitution and several shell commands. It is legitimate installation guidance, but it raises command execution risk.
中
Hidden file access
> mv inferencesh-cli-* ~/.local/bin/inferencesh
The command writes into a hidden home-directory path used for local executables. This is expected installation behavior, but it changes user executable search paths.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The hardcoded URL is used in an installer command that retrieves remote shell content. The network endpoint is expected, but it is security-relevant because it controls the script source.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The reinstall command fetches a remote installer script from a fixed URL. This is expected setup behavior, but it depends on a remote network source.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The hardcoded URL is part of a CLI installation command that fetches remote shell content. This network dependency is expected but security-relevant.
低
Hardcoded URL
](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwt
The Markdown image embeds a remote cloud.inference.sh asset. It is not code execution, but rendering the skill can trigger a third-party network request.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is used by the curl-to-shell install command. Fetching installer code from a fixed remote endpoint is security-relevant.
低
Hardcoded URL
> curl -LO https://dist.inference.sh/cli/checksums.txt
The command downloads checksums from a fixed remote endpoint. This is expected verification flow, but it is still a trusted network dependency.
低
Hardcoded URL
> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep
The command downloads and parses a remote manifest to select a binary URL. This network-controlled input influences the installation artifact.
风险因素
🌐 网络访问 (17)
🔑 环境变量 (3)
检测到的模式
Pipe to shell pattern×4
审计者: codex 查看审计历史 →
分享与引用此报告
分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。
复制报告链接
https://skillstore.io/skills/inference-sh-6-agent-tools/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/inference-sh-6-agent-tools?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/inference-sh-6-agent-tools?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-6-agent-tools/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/inference-sh-6-agent-tools.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>学术引用 (APA · BibTeX · CFF)
APA 引用
inference-sh-6. (2026). agent-tools security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-6-agent-tools/audits/4BibTeX 引用
@techreport{inference-sh-6-inference-sh-6-agent-tools-2026,
author = {inference-sh-6},
title = {agent-tools security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-6-agent-tools/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-tools security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-sh-6"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-sh-6-agent-tools/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-6-agent-tools:audit:4"
description: "Skillstore immutable audit report identifier"
比较变体
20 个可安装变体每位作者的技能都保持为独立的可安装项。推荐变体按 Skillstore 证据排序。
为什么此变体排名第一
Skillstore 使用量更高
作者 / 来源 Skillstore 评分 证据置信度 Skillstore 使用量 已更新
inference-skills-agent-tools
Skillstore 评分 38
证据置信度 中
Skillstore 使用量 44
已更新
2026-09-09
inference-sh-skills-agent-tools
Skillstore 评分 38
证据置信度 中
Skillstore 使用量 43
已更新
2026-09-09
inference-shell-agent-tools
Skillstore 评分 38
证据置信度 中
Skillstore 使用量 43
已更新
2026-09-09
inference-sh-6-agent-tools
Skillstore 评分 38
证据置信度 中
Skillstore 使用量 42
已更新
2026-09-09
halt-catch-fire-agent-tools
Skillstore 评分 38
证据置信度 中
Skillstore 使用量 38
已更新
2026-09-09
Skillstore 评分
评分依据 证据置信度: 中 45
架构
85
可维护性
87
内容
72
社区
91
规范符合性
你能构建什么
原型化多模态 AI 工作流
从一个 CLI 工作流中查找托管模型、生成示例输入、运行作业并检查任务结果。
快速创建媒体素材
无需管理本地 GPU 基础设施即可运行图像、视频、音频和 3D 生成应用。
比较托管模型能力
搜索应用目录、查看提供商选项，并使用受控输入测试 LLM、搜索和媒体应用。
试试这些提示
查找应用
Use agent-tools to find inference.sh apps for image generation. Show suitable options and explain when to use each one.
运行简单作业
Use agent-tools to run a hosted image app with this prompt: a clean product photo on a white background. Report the task result.
构建由示例驱动的工作流
Use agent-tools to get app details, generate a sample input file, explain the key fields, and run the app after I approve the input.
协调长时间运行的作业
Use agent-tools to submit a video generation job without waiting, capture the task ID, check status, and summarize the final output when ready.
最佳实践
- 在长时间作业之前确认应用命名空间、提供商和预期成本。
- 对复杂应用使用示例输入文件，以便在执行前查看参数。
- 在任何公开发布或账户操作前，审查输出和凭据。
避免
- 在未经验证的情况下，从不受信任的网络运行安装程序命令。
- 将私有数据发送到未知应用或提供商。
- 允许已认证账户执行无人值守的社交媒体操作。
常见问题
我需要 inference.sh 账户吗？
是的。必须先安装 CLI 并完成身份验证，才能运行大多数应用命令。
此技能可以运行图像和视频模型吗？
是的。它记录了图像、视频、音频、3D、LLM、搜索和实用工具应用类别。
它适用于 Claude、Codex 和 Claude Code 吗？
是的。marketplace 元数据将 Claude、Codex 和 Claude Code 列为受支持的工具。
结果来自哪里？
结果来自托管的 inference.sh 应用，并且可能包含生成文件的云 URL。
它可以发布到 Twitter/X 吗？
可以，前提是账户已配置。请在发帖、发送消息、关注、点赞或转发前确认具体操作。
发送敏感数据安全吗？
仅发送适合所选提供商和应用的数据。提交私有内容前请查看应用详情。
开发者详情
许可证
MIT
Skillstore 修订
r1
版本提示
作者未声明版本。
引用
a25199bc7d6b82598536822d1738eb5d5f54025b
维护新鲜度
2026/7/22
使用量
6 次下载 · 347 次浏览
文件结构
inference-sh-6 的更多技能
查看全部相关技能
查看全部📦
linear-projects-write
81从 CLI 管理 Linear 项目
由 Bind
团队需要快速、一致地设置 Linear 项目，而无需切换工具。此技能指导 Claude、Codex 和 Claude Code 使用 Bun CLI 创建和更新 Linear 项目。
效率 查看
📦
gws-gmail-watch
80使用 Pub/Sub 流监控 Gmail
由 googleworkspace
团队需要在 Gmail 收到新邮件时获得可靠通知。此技能帮助 Claude、Codex 和 Claude Code 使用 gws 监控 Gmail、过滤标签并流式传输结果。
效率 查看
📦
lark-doc
87安全管理 Lark 文档
由 larksuite
Lark 文档工作通常涉及跨多个命令的搜索、创建、更新和媒体处理。此技能为安全的 Lark 文档操作提供引导式 Claude、Codex 和 Claude Code 工作流。
办公与报告 查看
📦
native-transparent-imagegen
86Generate Native-Alpha Transparent Images
由 zseven-w
Image generators can return opaque files or painted checkerboards when transparency is required. This skill generates native-alpha assets and validates every untouched output.
设计与创意 查看
📦
pptx
85使用 Python 创建 PowerPoint 演示文稿
由 AutumnsGrove
手动制作精美的 PowerPoint 演示文稿耗时且难以复用。此技能指导 Claude、Codex 和 Claude Code 使用 python-pptx 进行 PPTX 创建、编辑和自动化。
办公与报告 查看
📦
building-agents
85构建 Claude Code 智能体
由 C0ntr0lledCha0s
创建可靠的 AI 智能体需要清晰的 schema、安全的工具和可重复的审查步骤。此技能为 Claude Code 工作流中的智能体设计、验证、迁移和维护提供指导。
编码与开发 查看