What makes AI 内容检测 AI Detect notable?

1.8K downloads. Trust evidence available

How should AI 内容检测 AI Detect be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

AI 内容检测 AI Detect

Detect whether an image, video, or audio file is AI-generated — including visual deepfakes and the likely generator model (Midjourney, Stable Diffusion, Sora, etc.). Returns confidence scores you can threshold. 检测图片、视频或音频是否由 AI 生成：包含人脸 deepfake 识别与疑似生成模型归因，返回可用于判定的置信度分数。

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.8k

Updated

Oct 10, 2026

Version

1.0.25

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.8K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.8K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.25release · observed Oct 8, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-detect

Install using `clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-detect` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/dlazyai/dlazy-detect before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-detect/snapshot"

Documentation

CLAWHUB

145,654 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: dlazy-detect
version: 1.0.5
description: "Detect whether an image, video, or audio file is AI-generated — including visual deepfakes and the likely generator model (Midjourney, Stable Diffusion, Sora, etc.). Returns confidence scores you can threshold. 检测图片、视频或音频是否由 AI 生成：包含人脸 deepfake 识别与疑似生成模型归因，返回可用于判定的置信度分数。"
metadata:
  {
    'clawdbot':
      {
        'emoji': '🔍',
        'requires': { 'bins': ['npm', 'npx'] },
        'install': 'npm install -g @dlazy/[email protected]',
        'installAlternative': 'npx @dlazy/[email protected]',
        'homepage': 'https://github.com/dlazy-ai/cli',
        'source': 'https://github.com/dlazy-ai/cli',
        'author': 'dlazyai',
        'license': 'see-repo',
        'npm': 'https://www.npmjs.com/package/@dlazy/cli',
        'configLocation': '~/.dlazy/config.json',
        'apiEndpoints': ['api.dlazy.com', 'files.dlazy.com'],
      },
    'openclaw': { 'systemPrompt': 'When invoking this skill, use dlazy detect -h for help.' },
  }
---

# AI 内容检测 AI Detect

[English](./SKILL.md) · [中文](./SKILL-cn.md)

Detect whether an image, video, or audio file is AI-generated — including visual deepfakes and the likely generator model (Midjourney, Stable Diffusion, Sora, etc.). Returns confidence scores you can threshold.

## Trigger Keywords

- detect
- ai-detect
- ai-generated
- deepfake
- is this AI

## What It Detects

- **Image / Video**: whether the visual is AI-generated (`ai_generated` score), whether it contains a **deepfake** (face swap), and the **likely generator** (Midjourney, Stable Diffusion, DALL·E, etc.).
- **Audio** (audio-only files, or the audio track of a video): whether the audio is AI-generated (`ai_generated_audio` score).
- **Text is NOT supported** by this model — image, video, and audio only.

> Recommended decision threshold: treat as AI-generated when the score is **≥ 0.9**. The skill already applies this to the `is_ai_generated` / `is_deepfake` booleans.
>
> Note: the underlying provider (Hive V3 Playground) has a default rate limit of **100 requests/day**.

## Authentication

All requests require a dLazy API key. The recommended way to authenticate is:

```bash
dlazy login
```

This runs a device-code flow (also works in remote shells) and **automatically saves your API key** to the local CLI config — no manual copy/paste required.

### Alternative: Set the Key Manually

```bash
dlazy auth set YOUR_API_KEY
```

The CLI saves the key in your user config directory (`~/.dlazy/config.json` on macOS/Linux, `%USERPROFILE%\.dlazy\config.json` on Windows). You can also supply the key per-invocation via the `DLAZY_API_KEY` environment variable.

### Getting Your API Key Manually

1. Sign in or create an account at [dlazy.com](https://dlazy.com)
2. Go to [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. Copy the key shown in the API Key section

## How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

- **Each `--ima

_meta.json

{
  "ownerId": "kn7c5wgeajfcfvdfb5ceemvdb984cjpd",
  "slug": "dlazy-detect",
  "version": "1.0.25",
  "publishedAt": 1791421390528
}

skill-card.md

## Description:

Checks images, videos, and audio for signs of AI generation, reporting confidence scores, possible deepfakes, and likely generators.

This skill is ready for commercial/non-commercial use.

## Publisher:

[dlazyai](https://clawhub.ai/user/dlazyai)

### License/Terms of Use:

MIT-0

## Use Case:

People and teams checking whether an image, video, or audio clip may be AI-generated use this skill to obtain confidence scores, deepfake indicators, and possible generator attribution.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Local images, videos, or audio can be uploaded to dLazy's hosted service without a prominent consent step.

Mitigation: Confirm the specific media before analysis; avoid sensitive files unless the service's privacy and retention terms are acceptable.

Risk: The login flow saves an API key in local CLI configuration.

Mitigation: Use a per-task API key when a saved credential is not desired, and protect any locally stored key.

## Reference(s):

- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-detect)
- [dLazy CLI repository (listed in skill metadata)](https://github.com/dlazy-ai/cli)
- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)

## Skill Output:

**Output Type(s):** [Text, Shell commands, Guidance]

**Output Format:** [Markdown with command examples and summarized JSON detection results]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Results can include confidence scores and likely generator; asynchronous requests return a task ID.]

## Skill Version(s):

1.0.25 (source: release metadata; skill frontmatter lists 1.0.5)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

SKILL-cn.md

---
name: dlazy-detect
version: 1.0.5
description: "检测图片、视频或音频是否由 AI 生成：包含人脸 deepfake 识别与疑似生成模型归因（Midjourney、Stable Diffusion、Sora 等），返回可用于判定的置信度分数。"
metadata:
  {
    'clawdbot':
      {
        'emoji': '🔍',
        'requires': { 'bins': ['npm', 'npx'] },
        'install': 'npm install -g @dlazy/[email protected]',
        'installAlternative': 'npx @dlazy/[email protected]',
        'homepage': 'https://github.com/dlazy-ai/cli',
        'source': 'https://github.com/dlazy-ai/cli',
        'author': 'dlazyai',
        'license': 'see-repo',
        'npm': 'https://www.npmjs.com/package/@dlazy/cli',
        'configLocation': '~/.dlazy/config.json',
        'apiEndpoints': ['api.dlazy.com', 'files.dlazy.com'],
      },
    'openclaw': { 'systemPrompt': '当调用此技能时，可以使用 dlazy detect -h 查看帮助信息。' },
  }
---

# AI 内容检测 AI Detect

[English](./SKILL.md) · [中文](./SKILL-cn.md)

检测图片、视频或音频是否由 AI 生成：包含人脸 deepfake 识别与疑似生成模型归因（Midjourney、Stable Diffusion、Sora 等），返回可用于判定的置信度分数。

## 触发关键词

- detect
- ai-detect
- ai-generated
- deepfake
- AI 检测
- 是不是 AI 生成

## 能检测什么

- **图片 / 视频**：是否 AI 生成（`ai_generated` 分数）、是否含 **deepfake**（换脸）、以及**疑似生成模型**（Midjourney、Stable Diffusion、DALL·E 等）。
- **音频**（纯音频文件，或视频里的音轨）：音频是否 AI 生成（`ai_generated_audio` 分数）。
- **不支持文字**——本模型仅支持图片、视频、音频。

> 推荐判定阈值：分数 **≥ 0.9** 视为 AI 生成。技能已按此阈值给出 `is_ai_generated` / `is_deepfake` 布尔结果。
>
> 注意：底层服务商（Hive V3 Playground）默认限速 **100 次/天**。

## 身份验证 (Authentication)

所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：

```bash
dlazy login
```

该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。

### 备选：手动设置 API Key

```bash
dlazy auth set YOUR_API_KEY
```

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\.dlazy\config.json`）。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。

### 手动获取 API Key

1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号
2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)
3. 复制 API Key 区域显示的密钥

## 工作原理

此技能是 dLazy 托管 API 的轻量封装。调用时：

- **`--image_url` / `--video_url` / `--audio_url` 既可以传本地文件路径，也可以传公开链接（URL）—— CLI 会自动判断是哪种。** 不用先上传、也不用做任何转换，有什么直接传就行。
  - **本地文件**（如 `./photo.jpg`、`C:\clip.mp4`）：CLI 会自动上传到 dLazy 媒体存储（`files.dlazy.com`），再把得到的 URL 传给后端。
  - **公开链接**（如 `https://example.com/a.png`）：原样透传。注意该链接必须**公开可访问**——需要登录/鉴权或在内网的链接，检测服务抓取不到。
- 媒体会被分析，返回结构化判定结果（AI 生成置信度、deepfake 置信度、疑似生成模型）。

## 使用方法

**CRITICAL INSTRUCTION FOR AGENT**:
执行 `dlazy detect`，并且只传 `--image_url`、`--video_url`、`--audio_url` 三者之一。

```bash
dlazy detect -h

Options:
  --image_url [image_url]              待检测的图片（本地路径或公开 URL）
  --video_url [video_url]              待检测的视频（本地路径或公开 URL）
  --audio_url [audio_url]              待检测的音频（本地路径或公开 URL）
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout <seconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help fo

Github ReposUpdated 9h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.