← 返回 Skills 市场
raghulpasupathi

Image Detection

作者 raghulpasupathi · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
837
总下载
0
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install image-detection
功能描述
Analyzes images to detect AI generation, extract metadata, identify artifacts, and perform content moderation using local and cloud-based tools.
使用说明 (SKILL.md)

Image Detection Skills

Skills for analyzing and detecting AI-generated images.

Essential Skills

1. Image Analyzer

Skill ID: image-analyzer

Purpose: Local image analysis without external APIs

Features:

  • EXIF metadata extraction
  • AI artifact detection (weird hands, blurred backgrounds)
  • Visual similarity comparison
  • Reverse image search integration

Installation:

npm install @clawhub/image-analyzer

Configuration:

{
  "skill": "image-analyzer",
  "settings": {
    "detectArtifacts": true,
    "extractMetadata": true,
    "localOnly": true,
    "checkSignatures": ["DALL-E", "Midjourney", "Stable-Diffusion"]
  }
}

Use Cases: Fast local detection, metadata verification, artifact identification

2. HuggingFace Image Detector

Skill ID: hf-image-detector

Purpose: ML-based AI image detection

Features:

  • Pre-trained models (umm-maybe/AI-image-detector)
  • High accuracy (90-95%)
  • Supports SD, Midjourney, DALL-E
  • Local inference (no API calls)

Installation:

npm install @clawhub/hf-image-detector

Use Cases: High-accuracy detection, privacy-focused analysis

3. Hive Moderation API

Skill ID: hive-api

Purpose: Cloud-based image analysis

Features:

  • AI-generated detection
  • NSFW filtering
  • Object detection
  • Fast inference (500ms)

Installation: API integration via REST

Use Cases: Quick detection, multi-purpose analysis, NSFW filtering

Installation

Via ClawHub

https://clawhub.ai/raghulpasupathi/image-detection

Via npm

npm install @raghulpasupathi/image-detection

Configuration Examples

High Accuracy Stack

{
  "skills": ["image-analyzer", "hf-image-detector", "hive-api"],
  "votingStrategy": "majority"
}

Privacy-Focused Stack

{
  "skills": ["image-analyzer", "hf-image-detector"],
  "externalAPIs": false
}

Fast Detection Stack

{
  "skills": ["hive-api"],
  "cacheResults": true
}

For video detection, see VIDEO_DETECTION.md.

安全使用建议
Before installing, verify the following: 1) Ask the publisher for a source repo or homepage and versioned releases—avoid running npm install on unknown scoped packages without reviewing their code. 2) Confirm how Hive Moderation or other cloud APIs are authenticated (the skill should declare required env vars like HIVE_API_KEY); never paste production credentials into an untrusted skill. 3) Be cautious with reverse image search or cloud-based moderation—these will upload images and could leak sensitive content. 4) If you need privacy, prefer the 'Privacy-Focused Stack' but still inspect the local npm packages for telemetry or build-time scripts. 5) Run installs in a sandbox, pin package versions, and review the packages' maintainers and license. If the publisher cannot provide a repository, clear credential-handling guidance, and package provenance, treat this skill as higher risk.
功能分析
Type: OpenClaw Skill Name: image-detection Version: 1.0.0 The skill bundle describes legitimate image detection functionalities and provides standard installation instructions using `npm install`. There is no evidence of intentional harmful behavior, data exfiltration, backdoors, or prompt injection attempts against the AI agent within the provided `_meta.json` or `SKILL.md` files. The `npm install` commands are presented as user-facing installation steps, not as commands for the agent to execute during its operation, and the content is purely descriptive and instructional.
能力评估
ℹ Purpose & Capability
The SKILL.md describes both local analysis and a cloud-based Hive moderation API, which matches the stated purpose. However the registry metadata claims no install steps, no required env vars, and no primary credential, which is inconsistent with a skill that integrates with external APIs and third-party npm packages.
⚠ Instruction Scope
Runtime instructions tell the agent to npm install several scoped packages and to integrate with the Hive Moderation REST API and reverse-image-search (which may upload images). The SKILL.md does not specify how API credentials should be provided or protected, nor does it limit what images may be sent to external services—this can lead to unintended data exfiltration.
⚠ Install Mechanism
There is no formal install spec in the registry, but SKILL.md instructs running npm install for scoped packages (@clawhub/* and @raghulpasupathi/*). Installing arbitrary npm packages at runtime is moderate risk: packages can execute code during install and are from unknown publishers. No pinned versions, checksums, or well-known release hosts are provided.
⚠ Credentials
The metadata declares no required environment variables or primary credential, yet the Hive API and some model hubs typically require API keys/tokens. This omission is a red flag—credentials are necessary for cloud services but are not declared or explained.
✓ Persistence & Privilege
The skill does not request always: true and has no declared system-wide persistence or privileges. It appears to be user-invocable and not forced into every agent run.
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 image-detection
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /image-detection 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
Initial release of image-detection skill, providing multiple methods for AI-generated image detection: - Introduces three detection skills: local analyzer, HuggingFace ML-based detector, and Hive Moderation API. - Supports EXIF metadata extraction, artifact detection, and reverse image search integration. - Offers local-only and privacy-focused detection options with no external API calls. - Enables high-accuracy, fast, and multi-purpose cloud-based analysis (including NSFW filtering). - Includes example configuration stacks for different detection needs.
元数据
Slug image-detection
版本 1.0.0
许可证 —
累计安装 5
当前安装数 5
历史版本数 1
常见问题

Image Detection 是什么？

Analyzes images to detect AI generation, extract metadata, identify artifacts, and perform content moderation using local and cloud-based tools. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 837 次。

如何安装 Image Detection？

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

Image Detection 是免费的吗？

是的，Image Detection 完全免费（开源免费），可自由下载、安装和使用。

Image Detection 支持哪些平台？

Image Detection 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 Image Detection？

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

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论