← 返回 Skills 市场
github2cao

薇薇发

作者 GitHub2Cao · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
158
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install 111jjjjk
功能描述
支持上传和处理图片、文件及CSV,结合输入内容生成定制化文本回复,适用于聊天记录和工作流应用场景。
使用说明 (SKILL.md)
  1. 首先要确认,图片、文件是保存多久. 跟聊天记录的时长是否一致。

spring.application.name.llm-playground-service

imagePaths 使用这个参数接图片 imagePath 单张 imagePaths 多张

filePaths 使用这个参数接文件 filePath 单个文件 filePaths 多个文件

本地调试 需要在header 中添加 currentuser 参数

http://10.73.171.38:30110/largemodel/llmstudio/fs/uploadImg 上传图片地址 http://10.73.171.38:30110/largemodel/llmstudio/fs/6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/1763357942287_CGM.png 显示地址 6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/1763357942287_CGM.png 返回内容

http://10.73.171.38:30110/largemodel/llmstudio/fs/6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/1763360443721_1763360443713_493caaf73fcc20446dc764987a53fad9.jpg 6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/1763360443721_1763360443713_493caaf73fcc20446dc764987a53fad9.jpg

http://10.73.171.38:30110/largemodel/llmstudio/fs/uploadFile 上传文件地址 文件没有显示 6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/error.txt 返回内容

工作流

文件上传:http://188.103.147.179:30181/largemodel/llmstudio/llm-workflow-service/api/v1/workflow/sign_file_url

{ "id": "6915755ec2e807195c7a8e6b", "input": { "BOT_USER_INPUT": "yyyyy", "BOT_CHAT_HISTORY": null, "BOT_USER_FILE": "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/1763015301444_CGM.png" }, "lastUpdate": "1763015276963", "canvasType": "DRAFT" } --- "reason": "illegal input, offset 1, char 由",

{ "browserEnable": true, "imagePath": null, "imagePaths": [ "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/1763030284427_10.30加班打卡记录.jpg", "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/1763030292138_11.04加班打卡记录.jpg" ], "filePaths": [ "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/2025.11.13-2025.11.21.txt", "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/2025.11.13-2025.11.21.txt", "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/上下班打卡_日报_20250720-20250920-30天.csv" ], "filePath": "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/2025.11.13-2025.11.21.txt", "recordId": "1762860012769ojonrbvlw", "video": { "videoImagePath": null, "videoPath": null, "duration": null }, "docId": null, "sourceDoc": { "type": 0, "list": [ { "name": "2025.11.13-2025.11.21.txt", "size": 6567, "status": "success", "path": "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/2025.11.13-2025.11.21.txt", "showRef": false }, { "name": "2025.11.13-2025.11.21.txt", "size": 6567, "status": "success", "path": "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/2025.11.13-2025.11.21.txt", "showRef": false }, { "name": "上下班打卡_日报_20250720-20250920-30天.csv", "size": 27923, "status": "success", "path": "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/上下班打卡_日报_20250720-20250920-30天.csv", "showRef": false } ] }, "params": {}, "modelId": "jiutian-lan", "input": "用文件内容吹牛逼", "sourceType": "app", "agentApp": { "appId": "690d98e00b367959f1fcc8dd", "appName": "cgm_test", "debug": true, "id": "690d98e00b367959f1fcc8dd", "name": "cgm_test", "avatar": "public/avatar/1762498777498_1762498777496_1762498777487_text2Image.jpg", "desc": "cgm_test", "prolog": null, "userId": "6e35a560-0530-4b72-8b1c-672f9bb5d531", "username": "cxy_test", "createTime": "2025-11-07 14:59:44", "updateTime": "2025-11-13 18:37:49", "modelId": "jiutian-lan", "params": {}, "prompt": "", "example": [ { "question": "帮忙吹牛逼", "file": { "path": "", "name": "", "type": "", "size": 0, "status": "", "message": "" } }, { "question": "", "file": { "path": "", "name": "", "type": "", "size": 0, "status": "", "message": "" } } ], "plugList": [], "mcpList": null, "workflowList": [ { "id": "690db390713cfa3eba14f836", "canvasType": "PRIVATE_RELEASE" } ], "showRefer": 0, "memory": 0, "userVisibleMemory": false, "showSuggestInput": 1, "bot_voice": null, "klFile": null, "klBases": [], "clickCount": 0, "appType": 6, "status": 0, "pubTime": null, "rejectReason": null, "offLineReason": null, "favoriteCount": null, "isRecommended": null, "recommendTime": null, "chatCount": 0, "topN": 3, "threshold": 0.65, "addContext": null, "rerank": 1, "rerankModel": "BAAI/bge-reranker-large", "searchType": 0, "answerModelId": "qwen3-32b", "temperature": 0.8, "topP": 0.5, "kbSearchModel": "forced", "chatMode": "workflow", "planModel": null, "cards": null, "mobileCertify": null, "goodCount": 0, "badCount": 0, "teamId": null, "coopUids": null, "coopUserInfo": null, "lastUpdateTime": null, "coopRole": "creater", "publishedTemplate": null, "agentCardId": null, "questionList": [ { "question": "帮忙吹牛逼", "file": { "path": "", "name": "", "type": "", "size": 0, "status": "", "message": "" } }, { "question": "", "file": { "path": "", "name": "", "type": "", "size": 0, "status": "", "message": "" } } ] } }

LLM 图片上传:http://188.103.147.179:30181/largemodel/llmstudio/fs/uploadImg 文件上传:http://188.103.147.179:30181/largemodel/llmstudio/fs/uploadFile csv上传:http://188.103.147.179:30181/largemodel/llmstudio/fs/uploadFile

请求参数 { "browserEnable": true, "imagePath": null, "filePath": null, "recordId": "1763016007604y5aej1it3", "video": { "videoImagePath": null, "videoPath": null, "duration": null }, "docId": null, "sourceDoc": { "type": 0, "list": [] }, "params": {}, "modelId": "jiutian-lan", "input": "123445", "name": "2323", "sourceType": "app", "agentApp": { "appId": "69157c599ddc670712531443", "appName": "cgm_test", "debug": true, "id": "69157c599ddc670712531443", "name": "cgm_test", "avatar": "public/avatar/1763015767084_CGM.png", "desc": "cgm_test", "prolog": null, "userId": "6e35a560-0530-4b72-8b1c-672f9bb5d531", "username": "cxy_test", "createTime": "2025-11-13 14:36:09", "updateTime": "2025-11-13 14:36:09", "modelId": "jiutian-lan", "params": {}, "prompt": "使用输入参数进行吹牛逼,吹越大越好!", "example": [ { "question": "", "file": { "path": "", "name": "", "type": "", "size": 0, "status": "", "message": "" } } ], "plugList": [], "mcpList": null, "workflowList": [], "showRefer": 0, "memory": 0, "userVisibleMemory": false, "showSuggestInput": 1, "klFile": null, "klBases": [], "clickCount": 0, "appType": 6, "status": 0, "pubTime": null, "rejectReason": null, "offLineReason": null, "favoriteCount": null, "isRecommended": null, "recommendTime": null, "chatCount": 0, "topN": 3, "threshold": 0.65, "addContext": null, "rerank": 1, "rerankModel": "BAAI/bge-reranker-large", "searchType": 0, "answerModelId": "Qwen3-32B", "temperature": 0.84, "topP": 0.5, "kbSearchModel": "forced", "chatMode": "llm", "planModel": "Qwen3-32B-fc", "cards": {}, "mobileCertify": 0, "goodCount": 0, "badCount": 0, "teamId": null, "coopUids": null, "coopUserInfo": null, "lastUpdateTime": null, "coopRole": "creater", "publishedTemplate": null, "questionList": [ { "question": "", "file": { "path": "", "name": "", "type": "", "size": 0, "status": "", "message": "" } } ] } }

请求参数 { "browserEnable": true, "imagePath": "6e35a560-0530-4b72-8b1c-672f9bb5d531/upload/1763016377381_CGM.png", "filePath": null, "recordId": "1763016347001xgjj90sl4", "video": { "videoImagePath": null, "videoPath": null, "duration": null }, "docId": null, "sourceDoc": { "type": 0, "list": [] }, "params": {}, "modelId": "jiutian-lan", "input": "用图片内容", "name": "用图片内容", "sourceType": "app", "agentApp": { "appId": "69157c599ddc670712531443", "appName": "cgm_test", "debug": true, "id": "69157c599ddc670712531443", "name": "cgm_test", "avatar": "public/avatar/1763015767084_CGM.png", "desc": "cgm_test", "prolog": null, "userId": "6e35a560-0530-4b72-8b1c-672f9bb5d531", "username": "cxy_test", "createTime": "2025-11-13 14:36:09", "updateTime": "2025-11-13 14:36:09", "modelId": "jiutian-lan", "params": {}, "prompt": "", "example": [ { "question": "", "file": { "path": "", "name": "", "type": "", "size": 0, "status": "", "message": "" } } ], "plugList": [], "mcpList": null, "workflowList": [], "showRefer": 0, "memory": 0, "userVisibleMemory": false, "showSuggestInput": 1, "klFile": null, "klBases": [], "clickCount": 0, "appType": 6, "status": 0, "pubTime": null, "rejectReason": null, "offLineReason": null, "favoriteCount": null, "isRecommended": null, "recommendTime": null, "chatCount": 0, "topN": 3, "threshold": 0.65, "addContext": null, "rerank": 1, "rerankModel": "BAAI/bge-reranker-large", "searchType": 0, "answerModelId": "Jiutian-75B", "temperature": 0.9, "topP": 0.5, "kbSearchModel": "forced", "chatMode": "llm", "planModel": "jiutian_75b_fc", "cards": {}, "mobileCertify": 0, "goodCount": 0, "badCount": 0, "teamId": null, "coopUids": null, "coopUserInfo": null, "lastUpdateTime": null, "coopRole": "creater", "publishedTemplate": null, "questionList": [ { "question": "", "file": { "path": "", "name": "", "type": "", "size": 0, "status": "", "message": "" } } ] } }

安全使用建议
This skill appears to do what it says (upload/process images and files), but it contains hard-coded upload endpoints (internal IPs and a public IP) and even an example bearer token in the bundled files. Before installing or using it: 1) Verify who controls the listed endpoints and whether you trust them — the skill will send uploaded user files to those hosts. 2) Ask the publisher how authentication is handled and why no credentials are declared in the manifest. 3) Do not upload sensitive files until you confirm retention and access policies for the endpoints. 4) Prefer running this only in an isolated/test environment or behind network controls (block outbound to those IPs) until you obtain clarification. If you cannot get clear answers about the endpoints and token handling, treat the skill as risky and avoid installing it.
功能分析
Type: OpenClaw Skill Name: 111jjjjk Version: 1.0.0 The bundle appears to be a collection of developer logs and API documentation rather than a functional skill. It contains significant information disclosure, including internal IP addresses (10.73.171.38), external staging IPs (188.103.147.179), and a hardcoded Bearer token in '2025.11.24-2025.11.28.txt'. While there is no evidence of intentional malice, the exposure of authentication credentials and internal infrastructure details constitutes a high-risk security vulnerability.
能力评估
Purpose & Capability
The name/description say it handles uploads and generates text from images/files, and the SKILL.md contains concrete upload and workflow endpoints and payloads consistent with that purpose. However, the skill hard-codes internal IP addresses and a public IP for upload/workflow endpoints without declaring that network access or credentials are required, which is a discrepancy worth flagging.
Instruction Scope
Runtime instructions instruct posting user images/files to several hard-coded endpoints (e.g., 10.73.171.38:30110 and 188.103.147.179:30181) and reference header 'currentuser' and an Authorization Bearer token in included logs—this means user data would be sent to those endpoints. The SKILL.md does not explain data retention, privacy, or who controls those endpoints, which is scope creep for a skill that claims only to 'process' files and reply with text.
Install Mechanism
There is no install spec and no code files to execute, so nothing is written to disk by an installation step. That reduces supply-chain risk, but runtime network calls described in the instructions remain the primary risk surface.
Credentials
The skill declares no required environment variables or credentials, yet the documentation and logs include an Authorization Bearer token and note using a currentuser header for uploads. Either required credentials are omitted from the manifest (mismatch) or the skill relies on ambient/implicit credentials — both are risky and disproportionate to the manifest.
Persistence & Privilege
The skill is user-invocable, not always-enabled, and does not request installation-time persistence or system-wide config changes. Autonomous invocation is allowed by default but is not combined here with 'always' or other privileged settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install 111jjjjk
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /111jjjjk 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
史蒂夫师弟发
元数据
Slug 111jjjjk
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

薇薇发 是什么?

支持上传和处理图片、文件及CSV,结合输入内容生成定制化文本回复,适用于聊天记录和工作流应用场景。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 158 次。

如何安装 薇薇发?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install 111jjjjk」即可一键安装,无需额外配置。

薇薇发 是免费的吗?

是的,薇薇发 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

薇薇发 支持哪些平台?

薇薇发 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 薇薇发?

由 GitHub2Cao(@github2cao)开发并维护,当前版本 v1.0.0。

💬 留言讨论