技能 happyhorse-1-0
📦
happyhorse-1-0
內容修訂 r1 中風險 ⚙️ 外部命令🌐 網路存取📁 檔案系統存取
使用 RunComfy 建立 HappyHorse 1.0 影片
影片創作者需要可靠的提示詞與設定來使用 HappyHorse 1.0，而不必猜測 API 結構描述。此技能會準備 RunComfy CLI 呼叫，並提供實用的提示詞指引，用於文字轉影片生成。
支援: Claude Codex Code(CC)
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 "happyhorse-1-0" from https://skillstore.io/skills/doany-ai-happyhorse-1-0.md and its manifest at https://skillstore.io/api/skills/doany-ai-happyhorse-1-0/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.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「happyhorse-1-0」。 帶有蒸氣、晨光和柔和環境音的直式咖啡館產品鏡頭。
預期結果:
此技能會選擇直式格式，建議八秒時長，並圍繞動作、質感和聲音來架構提示詞。
正在使用「happyhorse-1-0」。 一段雙鏡頭故事，同一名太空人穿越月球平原並回望地球。
預期結果:
此技能會在兩個鏡頭中重複太空人的身分，並建議一致的服裝、攝影機距離、光線和音訊提示。
正在使用「happyhorse-1-0」。 使用者要求由現有音訊檔案驅動的對嘴。
預期結果:
此技能會說明此範本僅適用於文字轉影片，並建議支援音訊驅動對嘴的模型。
安全審計
中風險v4 • 2026/7/5 開啟版本化報告
Most static backtick findings are Markdown examples, table values, endpoint names, or prompt samples rather than Ruby shell execution. The skill relies on local RunComfy CLI commands and a RunComfy API request with a bearer token. No prompt injection attempt or malicious exfiltration intent was found.
1
已掃描檔案
196
分析行數
9
複核項目
0
已忽略的誤報
已確認的安全問題 (1)
中
Third-Party Prompt and Token Transfer
The workflow sends user prompts to the RunComfy Model API and authenticates with a bearer token. Users should understand that prompt content leaves the local environment.
Lines 178-181 describe CLI submission, a POST to the RunComfy API with the bearer token, polling, and result retrieval. This is explicit third-party data transfer, not inferred behavior.
能力複核項目 (9)
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。
中
Ruby/shell backtick execution
Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through
The skill documentation intentionally directs the agent or user to run the local RunComfy CLI. External CLI execution can affect the host and submit data externally, so it requires user awareness and constrained arguments.
中
Ruby/shell backtick execution
```bash
The fenced example runs npx to add a skill from a GitHub source. That is real external command execution with package and supply-chain exposure.
中
Ruby/shell backtick execution
1. **RunComfy CLI** — `npm i -g @runcomfy/cli`
The prerequisite tells users to install the RunComfy CLI globally through npm. Global CLI installation is legitimate but has package supply-chain and host modification risk.
中
Ruby/shell backtick execution
2. **RunComfy account** — `runcomfy login` opens a browser device-code flow.
The prerequisite directs users to run runcomfy login, which opens an authentication flow and creates local credentials. That is expected but still a security-relevant command.
中
Ruby/shell backtick execution
```bash
The fenced example runs runcomfy with user-controlled prompt content and an output directory. The command is fixed, but it invokes a local CLI with network and filesystem effects.
中
Ruby/shell backtick execution
```bash
The fenced example runs runcomfy with user-controlled prompt content and an output directory. The command is fixed, but it invokes a local CLI with network and filesystem effects.
中
Ruby/shell backtick execution
```bash
The fenced example runs runcomfy with user-controlled prompt content and an output directory. The command is fixed, but it invokes a local CLI with network and filesystem effects.
中
Ruby/shell backtick execution
1. The skill invokes `runcomfy run happyhorse/happyhorse-1-0/text-to-video` with a JSON body matchin
The skill documentation intentionally directs the agent or user to run the local RunComfy CLI. External CLI execution can affect the host and submit data externally, so it requires user awareness and constrained arguments.
低
Hardcoded URL
2. The CLI POSTs to `https://model-api.runcomfy.net/v1/models/happyhorse/happyhorse-1-0/text-to-vide
The documented workflow posts requests to the RunComfy Model API using a bearer token. This is intentional network behavior, but it exposes prompts and credentials to a third-party service.
風險因素
⚙️ 外部命令 (40)
SKILL.md:10 SKILL.md:24-26 SKILL.md:26-44 SKILL.md:44-45 SKILL.md:45-46 SKILL.md:46 SKILL.md:50-54 SKILL.md:54-55 SKILL.md:55 SKILL.md:56 SKILL.md:57-58 SKILL.md:58-59 SKILL.md:59-65 SKILL.md:65-69 SKILL.md:69-73 SKILL.md:73-82 SKILL.md:82-86 SKILL.md:86-90 SKILL.md:90-92 SKILL.md:92 SKILL.md:98 SKILL.md:102-104 SKILL.md:104 SKILL.md:126-133 SKILL.md:133-137 SKILL.md:137-143 SKILL.md:143-147 SKILL.md:147-152 SKILL.md:152-158 SKILL.md:158-163 SKILL.md:163-169 SKILL.md:169-178 SKILL.md:178-179 SKILL.md:179-180 SKILL.md:180 SKILL.md:181 SKILL.md:182 SKILL.md:191 SKILL.md:192-194 SKILL.md:194
🌐 網路存取 (4)
📁 檔案系統存取 (5)
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/doany-ai-happyhorse-1-0/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/doany-ai-happyhorse-1-0?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/doany-ai-happyhorse-1-0?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-happyhorse-1-0/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/doany-ai-happyhorse-1-0.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
doany-ai. (2026). happyhorse-1-0 security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-happyhorse-1-0/audits/4BibTeX 引用
@techreport{doany-ai-doany-ai-happyhorse-1-0-2026,
author = {doany-ai},
title = {happyhorse-1-0 security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/doany-ai-happyhorse-1-0/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: "happyhorse-1-0 security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/doany-ai-happyhorse-1-0/audits/4"
identifiers:
- type: other
value: "skillstore:doany-ai-happyhorse-1-0:audit:4"
description: "Skillstore immutable audit report identifier"
比較變體
4 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 評分最高
作者 / 來源 Skillstore 評分 證據置信度 Skillstore 使用量 已更新
prime-skills 推薦
prime-skills-happyhorse-1-0
Skillstore 評分 69
證據置信度 中
Skillstore 使用量 2
已更新
2026-10-24
agentspace-so-happyhorse-1-0
Skillstore 評分 50
證據置信度 高
Skillstore 使用量 12
已更新
2026-10-22
Skillstore 評分
評分依據 證據置信度: 高 55
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
製作短篇品牌影片
建立精簡的 1080p 片段，具備一致角色、清楚動作和同步環境音。
製作電影感場景原型
在大型製作前測試攝影機語言、角色錨點、場景節奏和音訊方向。
自動化影片生成請求
準備有效的 RunComfy CLI 輸入，並了解預期的端點、輪詢和下載行為。
試試這些提示
生成基本片段
Use HappyHorse 1.0 to create a five second 16:9 video. The scene is a cyclist crossing a quiet bridge at sunrise.
建立直式社群廣告
Create a 9:16 HappyHorse 1.0 clip for a coffee brand. Show steam, hand motion, warm cafe sound, and no dialogue.
建立多鏡頭角色場景
Use HappyHorse 1.0 for two shots with the same detective in a gray coat. Keep wardrobe, lighting, and voice consistent.
規劃模型路由決策
I need a short video with native audio, stable character identity, and 1080p output. Decide if HappyHorse 1.0 is the right model.
最佳實務
- 描述隨時間發生的動作，而不是只描述靜態影像。
- 要求多鏡頭一致性時，請在每個鏡頭中重述角色錨點。
- 在要求最終 1080p 算圖前，先使用短版 720p 測試。
避免
- 不要在一個短片段中結合許多不相關的動作。
- 不要使用不支援的長寬比，或超過 15 秒的時長。
- 在未檢視第三方傳輸風險前，不要提交敏感提示詞內容。
常見問題
此技能會生成什麼？
它協助透過 RunComfy 生成 HappyHorse 1.0 文字轉影片片段。
它需要 RunComfy 帳號嗎？
是。此工作流程需要 RunComfy CLI，並使用 RunComfy 帳號或 token 進行驗證。
它可以建立圖片轉影片輸出嗎？
不行。此範本僅涵蓋文字轉影片端點。
支援哪些片段長度？
已記載的時長範圍是 3 到 15 秒。
提示詞內容會留在本機嗎？
不會。此工作流程會將提示詞請求傳送到 RunComfy Model API。
哪些工具可以使用此技能？
報告列出支援 Claude、Codex 和 Claude Code。