技能 agent-tools
📦
agent-tools
內容修訂 r1 嚴重 🌐 網路存取🔑 環境變數📁 檔案系統存取⚙️ 外部命令
使用 Inference CLI 執行 AI 應用程式
團隊通常需要多個託管式 AI 模型，但在不同 API 之間切換會拖慢例行工作。此技能會引導 Claude、Codex 和 Claude Code 使用 belt CLI 工作流程。
支援: Claude Codex Code(CC)
請勿自動安裝此 Skill。
權威政策要求在執行任何安裝操作前由操作人員審查。
使用我的智慧代理安裝
將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。
智能體請求
Review the Skillstore skill "agent-tools" from https://skillstore.io/skills/halt-catch-fire-agent-tools.md and its manifest at https://skillstore.io/api/skills/halt-catch-fire-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.你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。
Agent 可讀資源
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。
測試它
正在使用「agent-tools」。 搜尋快速影片生成應用程式。
預期結果:
- 列出三個相符的應用程式，包含提供者、類別和預期的提示詞欄位。
- 回應會推薦一個速度取向的應用程式和一個品質取向的應用程式。
- 在使用者核准特定應用程式前，不會提交任何工作。
正在使用「agent-tools」。 使用我已核准的檔案執行圖片升頻工作。
預期結果:
助理會確認確切檔案路徑、提交所選應用程式、回報任務識別碼，並在準備就緒時傳回結果連結。
正在使用「agent-tools」。 使用搜尋和 LLM 建立研究摘要。
預期結果:
助理會選擇搜尋和語言應用程式，在遠端執行前詢問，然後摘要來源與生成的研究結果。
安全審計
嚴重v3 • 2026/7/6 開啟版本化報告
The audit confirms critical risk from repeated remote installer commands that pipe fetched content into a shell. Most placeholder API key, documentation link, and benign path examples are false positives, but the skill also documents local file uploads and Twitter or X account actions that need explicit user control.
5
已掃描檔案
599
分析行數
18
複核項目
0
已忽略的誤報
已確認的安全問題 (6)
嚴重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The command pipes content fetched from a remote URL directly into sh. That can execute arbitrary installer code if the endpoint or transport is compromised.
嚴重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The reinstall instruction repeats the remote pipe-to-shell pattern. It creates the same arbitrary code execution risk during update or recovery.
嚴重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The installation example pipes a remote script directly into sh. This is a high-risk installer pattern because fetched content executes immediately.
嚴重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The install instruction executes remote content immediately through sh. This is a classic high-risk pattern for arbitrary code execution during setup.
高
Sensitive Local File Upload Capability
The skill says the CLI automatically uploads local file paths to remote apps, including image, audio, and media examples. An agent could expose local data if it selects paths without explicit user approval.
Both cited sections explicitly describe automatic local file uploads and show local path inputs. The risk is contextual data exposure, not just a path syntax match.
中
Social Media Account Action Automation
The skill advertises Twitter or X posting and account actions, including posts, media creation, direct messages, follows, likes, and retweets. These actions can affect user accounts and can enable spam or unauthorized activity if run without review.
The cited lines show a posting example, list account-action app names, and link a Twitter automation skill. The abuse risk depends on credentials and user approval, so severity is medium.
能力複核項目 (18)
這些是真實的本機能力，對此技能而言可能是預期行為，因此需要複核，但不會按已確認的惡意行為計分。
高
Ruby/shell backtick execution
> ```bash
The manual install block downloads artifacts, evaluates command substitution from a remote manifest, extracts an archive, and moves a binary into PATH. Those are real external command and supply-chain risks.
高
Shell command substitution
> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep
This command substitution derives a download URL from a remote manifest and passes it to curl. Remote manifest contents influence what binary is downloaded.
高
Template literal with command substitution
> ```bash
The manual install snippet combines remote downloads, command substitution, archive extraction, and installing a binary into PATH. This is a real supply-chain execution risk.
高
Hidden file in home directory
> mv inferencesh-cli-* ~/.local/bin/inferencesh
The manual install moves a downloaded binary into ~/.local/bin, adding an external executable to the user PATH. This is a standard location but a real trust risk.
中
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
The line tells users to run npx to install another skill, which can execute package manager code and modify the agent environment. This is expected setup, but it is a real supply-chain action.
中
Ruby/shell backtick execution
```bash
The bash block includes a remote installer and a login command. Even though it is documentation, it guides execution of external commands during setup.
中
Ruby/shell backtick execution
```bash
The quick examples run cloud apps and include a Twitter post command, so they can send prompts or account actions to external services. The commands are core functionality but still security-relevant.
中
Ruby/shell backtick execution
```bash
The local file upload examples run belt commands that send local image, audio, or media paths to remote apps. This can expose local data if used without confirmation.
中
Ruby/shell backtick execution
| Run app | `belt app run google/veo-3-1-fast --input input.json` |
The command runs a remote app using local input, which may transmit data and incur side effects depending on the app. It is intended functionality but security-relevant.
中
Ruby/shell backtick execution
| Run without waiting | `belt app run <app> --input input.json --no-wait` |
The no-wait command submits a remote job in the background, so it can continue consuming resources after the agent returns. It should require clear user intent.
中
Ruby/shell backtick execution
```bash
The related-skills block tells users to run multiple npx skill installation commands. Installing additional skills can expand agent capabilities and supply-chain exposure.
中
Hidden file access
> mv inferencesh-cli-* ~/.local/bin/inferencesh
The command writes an installed binary under a hidden home-directory path. It is normal user-local installation, but it changes executable state.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
This URL is fetched as part of an installer command, so users must trust a remote endpoint before installing software. The network call is expected, but it is a real supply-chain trust boundary.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
This reinstall command fetches the installer from an external URL. It is intended setup behavior, but it still depends on remote code delivery.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is used in the CLI installation command. It is expected for setup, but it introduces an external software delivery dependency.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is fetched as the source of a pipe-to-shell installer. The network destination is expected, but it is part of a real installer trust boundary.
低
Hardcoded URL
> curl -LO https://dist.inference.sh/cli/checksums.txt
This command downloads a checksum file from an external distribution host as part of manual install. The network access is expected but part of the software supply chain.
低
Hardcoded URL
> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep
This command fetches a remote manifest to choose a binary download URL. The network response influences the installation flow.
風險因素
🌐 網路存取 (17)
🔑 環境變數 (3)
📁 檔案系統存取 (5)
⚙️ 外部命令 (21)
SKILL.md:7 SKILL.md:17-20 SKILL.md:20-22 SKILL.md:22-25 SKILL.md:25-34 SKILL.md:34-38 SKILL.md:38-56 SKILL.md:56-62 SKILL.md:62-74 SKILL.md:74-80 SKILL.md:80-81 SKILL.md:81-82 SKILL.md:82-83 SKILL.md:83-84 SKILL.md:84-85 SKILL.md:85-86 SKILL.md:86-87 SKILL.md:87-103 SKILL.md:103-129 SKILL.md:28 SKILL.md:25-34
偵測到的模式
Pipe to shell pattern×4
審計單位: codex 檢視審計紀錄 →
分享與引用此報告
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。
複製報告連結
https://skillstore.io/skills/halt-catch-fire-agent-tools/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/halt-catch-fire-agent-tools?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/halt-catch-fire-agent-tools?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/halt-catch-fire-agent-tools/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/halt-catch-fire-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>學術引用 (APA · BibTeX · CFF)
APA 引用
halt-catch-fire. (2026). agent-tools security audit report (audit version 3) [Author version unspecified]. Skillstore. https://skillstore.io/skills/halt-catch-fire-agent-tools/audits/3BibTeX 引用
@techreport{halt-catch-fire-halt-catch-fire-agent-tools-2026,
author = {halt-catch-fire},
title = {agent-tools security audit report (audit version 3)},
institution = {Skillstore},
year = {2026},
number = {3},
url = {https://skillstore.io/skills/halt-catch-fire-agent-tools/audits/3},
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 3)"
version: "unspecified"
type: report
authors:
- name: "halt-catch-fire"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/halt-catch-fire-agent-tools/audits/3"
identifiers:
- type: other
value: "skillstore:halt-catch-fire-agent-tools:audit:3"
description: "Skillstore immutable audit report identifier"
比較變體
20 個可安裝變體每位作者的技能都保留為獨立的可安裝項目。推薦變體依 Skillstore 證據排序。
為何此變體排名第一
Skillstore 使用量較高
作者 / 來源 Skillstore 評分 證據置信度 Skillstore 使用量 已更新
inference-skills-agent-tools
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 47
已更新
2026-09-09
inference-sh-skills-agent-tools
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 46
已更新
2026-09-09
inference-shell-agent-tools
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 46
已更新
2026-09-09
halt-catch-fire-agent-tools
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 41
已更新
2026-09-09
Skillstore 評分
評分依據 證據置信度: 中 45
架構
85
可維護性
87
內容
67
社群
91
規範符合度
你可以打造什麼
建立多模態工作流程原型
探索圖片、影片、音訊、搜尋和 LLM 應用程式，然後在同一個 CLI 流程中比較輸入與輸出。
自動化媒體生成任務
執行託管式圖片、影片、升頻、虛擬化身和工具型應用程式，而不需要管理本機 GPU 基礎架構。
從代理程式執行研究工作
在代理程式工作階段中使用搜尋和 LLM 應用程式，然後追蹤任務狀態並擷取結果連結。
試試這些提示
尋找應用程式
使用 agent-tools 搜尋 inference.sh 應用程式商店中的圖片生成應用程式。顯示三個選項和必要輸入。
執行簡單工作
使用 agent-tools 依照我的提示詞準備一個小型文字轉圖片工作。提交遠端工作前先詢問我。
追蹤長時間工作
使用 agent-tools 提交影片生成工作，但不要等待完成。接著顯示狀態檢查和結果擷取步驟。
建構多步驟工作流程
使用 agent-tools 探索應用程式、生成範例輸入、執行圖片轉影片工作流程，並在執行前摘要說明每個遠端動作。
最佳實務
- 在安裝 CLIs、上傳檔案或發布到外部服務前，先要求明確核准。
- 執行不熟悉的應用程式前，先生成範例輸入。
- 可用時固定應用程式版本，以建立可重複的工作流程。
避免
- 不要在無人值守的工作流程中將遠端安裝程式 pipe 到 shell。
- 不要將範圍過大的目錄或敏感本機檔案作為應用程式輸入上傳。
- 未經使用者審閱文字和確認帳戶前，不要使用社群媒體動作。
常見問題
此技能需要帳戶嗎？
是。它需要透過 belt login 或 API key 進行 inference.sh 驗證。
它可以在本機執行模型嗎？
否。它會透過 inference.sh 將請求傳送到雲端應用程式。不需要本機 GPU 硬體。
它可以上傳本機檔案嗎？
可以。CLI 可以上傳作為輸入傳入的檔案路徑。執行前請檢查路徑。
它可以發布到 Twitter 或 X 嗎？
此技能記錄了 X 自動化應用程式。僅在明確核准且具備有效憑證時使用它們。
它能在 Claude Code 和 Codex 中運作嗎？
可以。它宣告支援 Claude、Codex 和 Claude Code。
執行命令前我應該檢查什麼？
確認應用程式名稱、輸入結構描述、費用、憑證、檔案路徑和變更帳戶的動作。
開發者詳細資訊
授權
MIT
Skillstore 修訂
r1
版本提示
作者未聲明版本。
引用
a06681402992ceae98ba04d54cfd4ab004862696
維護新鮮度
2026/7/18
使用量
3 次下載 · 0 次瀏覽
檔案結構