技能 infsh-cli
📦
infsh-cli
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
從 inference.sh CLI 執行 AI 應用程式
AI 團隊經常在許多模型 API 和工具之間切換。此技能會引導 Claude、Codex 和 Claude Code 完成 inference.sh CLI 任務。
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 "infsh-cli" from https://skillstore.io/skills/halt-catch-fire-infsh-cli.md and its manifest at https://skillstore.io/api/skills/halt-catch-fire-infsh-cli/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「infsh-cli」。 尋找一個適合山景無人機鏡頭的快速影片生成應用程式。
預期結果:
助理會推薦合適的影片應用程式，列出必要輸入欄位，估計可能等待時間，並在花費點數前詢問。
正在使用「infsh-cli」。 將我的產品照片轉成一段短社群影片。
預期結果:
助理會確認本機檔案路徑，選擇 image-to-video 應用程式，描述上傳步驟，並等待核准。
正在使用「infsh-cli」。 檢查我長時間執行的生成任務結果。
預期結果:
助理會擷取任務狀態，摘要進度，並說明在哪裡可以找到已完成的媒體連結。
安全審計
嚴重v4 • 2026/7/9 開啟版本化報告
The skill is a community CLI integration that intentionally runs external commands and contacts inference.sh services. The remote installer uses curl piped to sh in multiple files, and local file upload plus Twitter/X automation create high-impact side effects that require explicit user confirmation.
5
已掃描檔案
608
分析行數
27
複核項目
0
已忽略的誤報
已確認的安全問題 (7)
嚴重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The command downloads a remote script and executes it immediately with sh. Users and agents cannot inspect or pin the installer before execution.
嚴重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The reinstall path repeats the same curl-to-shell installer pattern. This remains a critical supply-chain execution risk even if the endpoint is legitimate.
嚴重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The CLI reference repeats the curl-to-shell installer. Direct execution of remote installer code is a critical supply-chain pattern.
嚴重
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The primary install instruction pipes a remote script directly to sh. This is a critical remote-code execution and supply-chain pattern.
高
Automatic Local File Uploads to External Apps
The skill tells agents that the CLI automatically uploads local paths when supplied as inputs. This can disclose private files if a model selects paths without explicit user approval.
Both cited sections explicitly describe automatic uploads of local paths and show absolute, relative, and home-directory examples. The risk depends on user approval, but the capability is clearly documented.
高
Social Media Account Actions
The skill includes Twitter/X posting, media posting, direct message, follow, like, and retweet workflows. These actions can affect external accounts and require explicit user confirmation.
The skill names concrete Twitter/X commands for posting and related account interactions. These are intentional capabilities, not just pattern matches.
高
Broad Belt Command Permission
The skill grants Bash access to all belt subcommands, while the reference includes deployment and source-pull operations. This broad permission expands the blast radius beyond simple app execution.
The allowed-tools entry permits belt with any arguments, and the CLI reference documents development commands such as deploy and pull. The exact account impact depends on credentials, so confidence is high but not absolute.
能力複核項目 (27)
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。
嚴重
Ruby/shell backtick execution
```bash
The fenced shell block includes curl piped to sh followed by login. The installer step executes remotely downloaded code before local inspection.
高
Ruby/shell backtick execution
> ```bash
The manual install block downloads remote assets, parses a remote manifest, verifies checksums, extracts an archive, and moves an executable into PATH. This is a legitimate install flow but has supply-chain and local persistence risk.
高
Ruby/shell backtick execution
```bash
These commands run belt with local media paths that are automatically uploaded to external apps, and one example posts media to X/Twitter. That creates data disclosure and account-action risk.
高
Shell command substitution
> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep
The command builds a download URL from a remote manifest using shell command substitution. Even in documentation, this dynamic install pattern is risky and hard to audit.
高
Template literal with command substitution
> ```bash
The manual install block contains dynamic command substitution inside a remote download flow. This makes the installer path less transparent and increases supply-chain risk.
高
Hidden file in home directory
> mv inferencesh-cli-* ~/.local/bin/inferencesh
The manual install flow moves a downloaded executable into ~/.local/bin, placing persistent code in the user PATH. It is user-directed but has real local persistence impact.
中
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
The line instructs users to install another skill through npx, which performs a network package operation. This is legitimate setup guidance but carries supply-chain risk.
中
Ruby/shell backtick execution
```bash
The quick examples run hosted apps through belt, including web search and Twitter posting. These external CLI actions can create network and account side effects.
中
Ruby/shell backtick execution
```
The range transitions into a command table and includes a remote app-store operation. The pattern is broad, but it does point to external CLI activity.
中
Ruby/shell backtick execution
| Browse the app store | `belt app store` |
The belt app store command queries the public app store over the network. There is no injection evidence, but it is still external command execution.
中
Ruby/shell backtick execution
| Search the store | `belt app store search "flux"` |
The store search command sends a user query to the external service. This is intended behavior, but it is a real networked CLI operation.
中
Ruby/shell backtick execution
| Filter by category | `belt app store --category image` |
Filtering the remote app store still invokes the external belt CLI service. The risk is limited but the command has network side effects.
中
Ruby/shell backtick execution
| List your apps | `belt app list` |
Listing user apps queries account-specific remote data through belt. This can expose workspace metadata to the agent and terminal output.
中
Ruby/shell backtick execution
| Get app details | `belt app get google/veo-3-1-fast` |
Getting app details calls the external service for app metadata and schemas. It is expected functionality but remains a networked CLI action.
中
Ruby/shell backtick execution
| Generate sample input | `belt app sample google/veo-3-1-fast --save input.json` |
Generating a sample input can fetch app schema data and write an input file locally. This is legitimate but still an external command with filesystem effects.
中
Ruby/shell backtick execution
| Run app | `belt app run google/veo-3-1-fast --input input.json` |
Running an app submits user-provided inputs to a hosted service. This is the core feature, but it can transmit data and incur external side effects.
中
Ruby/shell backtick execution
| Run without waiting | `belt app run <app> --input input.json --no-wait` |
Running without waiting submits a background task to the hosted service. This can transmit data and consume account resources asynchronously.
中
Ruby/shell backtick execution
| Check task status | `belt task get <task-id>` |
Checking task status retrieves remote task data and results through the external CLI. It is intended, but it remains account-scoped external command execution.
中
Ruby/shell backtick execution
```bash
The related skills block uses npx commands to install multiple additional remote skills. That expands the trusted code surface and introduces package supply-chain risk.
中
Hidden file access
> mv inferencesh-cli-* ~/.local/bin/inferencesh
The same install flow writes into a hidden home-directory path. This is normal for user binaries, but it still modifies persistent executable search paths.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is used in a curl pipeline to a shell installer, so it drives network download for executable code. The hardcoded domain is expected for setup but still creates remote code supply-chain risk.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is used in a reinstall command that pipes a remote script to the shell. This is an expected installer endpoint, but it is still executable network content.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The hardcoded URL appears inside the CLI installation command that executes remote content. It is legitimate setup documentation but still a network execution dependency.
低
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is used in the curl-to-shell install command. The endpoint is expected, but it directly supplies executable installer content.
低
Hardcoded URL
> **What does the installer do?** The [install script](https://cli.inference.sh) detects your OS and
The link points to the install script discussed by the setup instructions. It is not execution by itself, but it supports the remote installer flow.
低
Hardcoded URL
> curl -LO https://dist.inference.sh/cli/checksums.txt
The command downloads checksums from a hardcoded distribution endpoint during manual install. This is legitimate verification support but still an external install dependency.
低
Hardcoded URL
> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep
The command fetches a remote manifest to select an installer artifact. This is an external dependency in an 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 (22)
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:87-88 SKILL.md:88-104 SKILL.md:104-130 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-infsh-cli/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/halt-catch-fire-infsh-cli?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/halt-catch-fire-infsh-cli?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/halt-catch-fire-infsh-cli/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/halt-catch-fire-infsh-cli.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). infsh-cli security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/halt-catch-fire-infsh-cli/audits/4BibTeX 引用
@techreport{halt-catch-fire-halt-catch-fire-infsh-cli-2026,
author = {halt-catch-fire},
title = {infsh-cli security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/halt-catch-fire-infsh-cli/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: "infsh-cli security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "halt-catch-fire"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/halt-catch-fire-infsh-cli/audits/4"
identifiers:
- type: other
value: "skillstore:halt-catch-fire-infsh-cli:audit:4"
description: "Skillstore immutable audit report identifier"
比較變體
9 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-infsh-cli
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 47
已更新
2026-09-09
inference-sh-skills-infsh-cli
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 43
已更新
2026-09-09
halt-catch-fire-infsh-cli
Skillstore 評分 38
證據置信度 中
Skillstore 使用量 35
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
83
規範符合度
你可以打造什麼
建立媒體素材
透過託管模型應用程式生成影像、影片、頭像、音訊和 3D 素材。
評估模型工作流程
從單一 CLI 工作流程中探索應用程式、檢查結構描述、執行範例，並比較模型輸出。
執行已核准的外部操作
在確認提示詞、媒體和帳戶操作後，使用搜尋應用程式或已核准的 Twitter/X 工作流程。
試試這些提示
尋找應用程式
尋找一個用於影像生成的 inference.sh 應用程式。顯示最佳選項，並說明哪一個適合我的提示詞。
執行簡單任務
使用 inference.sh 根據這個提示詞生成一張影像。在執行任何會花費點數的命令前先詢問我。
安全使用本機媒體
使用我的本機檔案準備一次 image-to-video 執行。上傳前先向我確認確切檔案路徑。
編排多步驟工作
規劃一個工作流程：搜尋網路、草擬媒體提示詞、執行影片模型，並追蹤任務直到完成。
最佳實務
- 執行命令前，先確認應用程式名稱、輸入、成本和會變更帳戶的操作。
- 提交昂貴或長時間執行的作業前，先使用範例輸入和應用程式結構描述。
- 允許 CLI 上傳檔案前，先檢查每個本機檔案路徑。
避免
- 不要在未驗證的情況下，將遠端安裝程式腳本 pipe 進 shell。
- 不要讓代理在未經使用者核准的情況下選擇本機檔案路徑。
- 不要在沒有最終使用者預覽的情況下，自動化 Twitter/X 發文或傳訊。
常見問題
這項技能能協助什麼？
它協助代理使用 inference.sh belt CLI 來尋找應用程式、執行託管模型作業並追蹤結果。
它需要帳戶嗎？
是。你需要 inference.sh 憑證，且某些作業可能需要點數或供應商存取權。
它可以執行影像和影片模型嗎？
可以。參考資料包含影像、影片、音訊、文字、搜尋、3D 和工具類應用程式範例。
它可以上傳本機檔案嗎？
可以。CLI 可以為相容應用程式上傳本機路徑，因此使用前請確認每個路徑。
它可以發文到 Twitter/X 嗎？
可以，該技能列出 Twitter/X 應用程式範例。使用者應在執行前核准確切文字和媒體。
自動安裝安全嗎？
不建議。目前的指示包含遠端安裝程式執行，因此建議手動驗證。
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
3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88
維護新鮮度
2026/7/18
使用量
3 次下載 · 0 次瀏覽
檔案結構