Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

image-enlarge

v1.0.2

通过 Flyelep AI 工具接口对图片进行无损放大,支持单张或批量处理。 当用户要求提升清晰度、放大图片尺寸、做超清增强、批量增强商品图时使用此技能。

0· 147·0 current·0 all-time
byflyelep@flyelepai

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for flyelepai/flyelep-image-enlarge.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "image-enlarge" (flyelepai/flyelep-image-enlarge) from ClawHub.
Skill page: https://clawhub.ai/flyelepai/flyelep-image-enlarge
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install flyelepai/flyelep-image-enlarge

ClawHub CLI

Package manager switcher

npx clawhub@latest install flyelep-image-enlarge
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description match the instructions: the SKILL.md consistently documents calling Flyelep's enlarge API to upsample images (single or batch). No unrelated binaries, installs, or capabilities are requested.
Instruction Scope
Instructions are narrowly scoped to: collect public image URLs, construct a POST request to the Flyelep endpoint with a 'secretKey' header, and return the returned image URLs. The doc explicitly forbids reading or persisting keys and instructs to not 'read' image contents. Note: ensure the agent does not prompt for or exfiltrate other system files or environment data—SKILL.md itself does not request those.
Install Mechanism
Instruction-only skill with no install steps or downloaded artifacts. This is low risk from an install-perspective.
!
Credentials
SKILL.md requires a Flyelep 'secretKey' to be supplied in the request header at runtime, but the registry metadata lists no required credentials/primaryEnv and the skill has no homepage or source to verify where keys are registered. This mismatch and the unknown provenance raise concern: users must provide an API key to an external domain (flyelep.cn), and the skill does not declare how keys should be managed by the platform.
Persistence & Privilege
always is false and the skill is user-invocable only. The skill does not request persistent installation or elevated platform privileges.
What to consider before installing
This skill calls an external API (https://www.flyelep.cn/...) and requires a 'secretKey' you must provide at runtime. Before using: 1) Confirm the Flyelep service and where to obtain the API key (the SKILL has no homepage/source); 2) Never paste your key into public chat or store it in an unprotected place—prefer providing it via the agent's secure credential input if available; 3) Prefer testing with non-sensitive, public image URLs first (do not supply private or personal images as URLs); 4) If possible, verify Flyelep's terms, privacy, and that the endpoint is legitimate; 5) If the platform expects skills to declare required credentials, ask the author/maintainer to declare the primaryEnv or provide provenance. These checks reduce risk from unknown-source skills that ask you to send secrets or data to an external service.

Like a lobster shell, security has layers — review code before you run it.

latestvk97as87h1g77cxcbhwcjr7fwp585nzer
147downloads
0stars
3versions
Updated 9h ago
v1.0.2
MIT-0

Flyelep 无损放大

通过 Flyelep AI Tool API 对图片进行无损放大处理,并返回增强后的图片 URL。

重要:这是一个 HTTP API 调用技能。必须通过 HTTP POST 请求调用 API 接口,禁止通过浏览器访问 Flyelep 网站。

API 接口信息

  • URL: POST https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/enlarge
  • Content-Type: application/json
  • 认证方式: 在请求头中传入 secretKey
  • 超时时间: 建议 120-300 秒

认证方式

所有 AI 工具接口均需在请求头中传入 secretKey。该密钥需由用户在 Flyelep 开放平台申请获得:https://www.flyelep.cn/controlboard

请求头示例:

Content-Type: application/json
secretKey: 用户提供的API密钥

安全说明secretKey 必须放在请求头中,这是 AI 工具接口的统一鉴权要求。不要将真实密钥写入技能文件、示例代码仓库或持久化配置中,应在运行时由用户动态提供。

请求 Body

{
  "imgUrls": "https://example.com/img1.jpg,https://example.com/img2.jpg",
  "scalingRatio": 2
}

响应格式

统一响应结构:

{
  "code": 200,
  "msg": "操作成功",
  "data": "https://example.com/enlarged1.jpg,https://example.com/enlarged2.jpg"
}
  • code=200 表示调用成功
  • msg 为接口返回说明
  • data 为放大后的图片地址
  • 多张图片时,data 中多个 URL 以英文逗号 , 分隔

返回结果应按逗号拆分后逐个展示给用户,不要回读图片内容。

参数说明

必传参数

字段默认值说明
imgUrls-图片链接字符串,多张时使用英文逗号分隔
scalingRatio-增强强度:1=轻度增强2=标准增强3=强力增强

参数映射规则

imgUrls

  • 接口要求传字符串,不是数组
  • 单张图片时直接传一个 URL 字符串
  • 多张图片时,用英文逗号 , 按顺序拼接
  • 每个链接都应为公网可访问的图片直链,不要传网页地址

scalingRatio

  • 1:轻度增强,适合原图质量较好、只需温和提清晰度
  • 2:标准增强,适合作为默认值
  • 3:强力增强,适合原图较糊或需要更明显提升

推荐默认规则:

  • 用户未指定增强强度时,默认传 2
  • 用户强调“轻微增强、尽量自然”时,传 1
  • 用户强调“尽可能清晰、强力修复”时,传 3

说明:PDF 文档额外提示“AI 超清有较严格的图片规格限制,文档中已注明”,但当前可提取页面未包含该规格细则。因此调用前应优先使用常见、清晰、可公开访问的图片直链;若接口报规格错误,应以 Flyelep 最新文档或控制台提示为准。

调用示例

单张图片标准增强:

curl -X POST "https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/enlarge" \
  -H "Content-Type: application/json" \
  -H "secretKey: 你的密钥" \
  --max-time 300 \
  -d '{
    "imgUrls": "https://example.com/img1.jpg",
    "scalingRatio": 2
  }'

批量图片强力增强:

curl -X POST "https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/enlarge" \
  -H "Content-Type: application/json" \
  -H "secretKey: 你的密钥" \
  --max-time 300 \
  -d '{
    "imgUrls": "https://example.com/img1.jpg,https://example.com/img2.jpg",
    "scalingRatio": 3
  }'

常见错误及解决方案

错误原因与解决
HTTP 401 / code 非 200secretKey 无效、缺失或已过期,确认请求头是否正确传入
HTTP 405 Not Allowed请求方法错误,必须使用 POST
imgUrls 格式错误该字段必须是字符串,多张图用英文逗号分隔,不是 JSON 数组
图片 URL 无法访问传入的链接不是公网直链、已过期,或源站限制访问
scalingRatio 非 1/2/3增强强度只支持 123
接口提示图片规格不符合要求Flyelep AI 超清对源图可能有限制,换用更规范的图片尺寸或格式后重试
请求超时批量图片较多或增强强度较高时,可适当增大超时时间

提示词处理

该接口不接收自然语言提示词,不需要构造额外文案。

执行时只需要:

  1. 收集一张或多张图片 URL
  2. 将多张 URL 用英文逗号拼接为 imgUrls
  3. 根据用户意图确定 scalingRatio
  4. 在请求头中传入 secretKey
  5. 调用接口并将返回的结果按逗号拆分后逐个展示

如果用户只是说“帮我变清晰一点”,优先使用默认的 scalingRatio=2;如果用户特别强调“不要过度锐化”,则使用 1

Comments

Loading comments...