Beacon Threat Intelligence
Security intelligence for the agent supply chain
Every MCP server and agent skill the public registries list, matched to its source repository, with Beacon's rating of what it can do to your agent and your machine.
| Name | Risk |
|---|---|
| Pdf Extractor Skill Extract text and LaTeX formulas from academic PDFs in English and Chinese, outputting structured Markdown with math, tables, and images preserved. | |
| TribuRuby Training Agent Helps users check in rituals, track streaks, and view tribe activity on TribuRuby. | |
| stock-manage-skill 股票管理技能，支持股票订单管理、交易规则管理和股票信息获取。支持A股、港股、美股等多种股票类型，使用本地文本目录存储数据。Use when user wants to manage stock orders, trading rules or get stock information including add... | |
| code-risk-agent 当用户需要扫描代码安全漏洞、审计代码、分析 C/Python 风险、检查依赖漏洞、或生成安全报告时触发。支持云端 LLM 语义分析和本地 GPU 回退。 | |
| Xiaohongshu Assistant Operator Automates daily Xiaohongshu content creation, publishing, marketing, and engagement for creator ID 4740535877 with strict persona and promotion controls. | |
| Agent-Friendly Design Design websites and applications that AI agents can consume, navigate, and interact with. Use when building any site, app, or product that agents will use as... | |
| Design Review Core pack — always active for visual work. Quality gate for UI, components, pages, layouts, or frontend work. Triggers on any visual/design task automaticall... | |
| UI Polish Pass Core pack — always active as final step. Visual polish pass for spacing, hierarchy, alignment, and cleanup. Runs after design-review and ux-baseline-check as... | |
| UX Baseline Check Core pack — always active for visual work. Enforces UX quality standards on any screen, flow, form, or dashboard. Ensures nothing ships with missing states.... | |
| Web Animation Design Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion, e... | |
| Whimsical Design Creates visually lively, warm, and playful designs with personality, motion, bold aesthetics, tactile textures, and purposeful color to evoke delight and bra... | |
| World Build Creates immersive digital environments by defining world context, atmosphere, typography, animations, and thematic UI to evoke specific emotions and depth. | |
| XQE Agent Team Orchestrate a dynamic multi-agent team where a lead agent (opus) plans and delegates tasks to specialized worker agents (sonnet) that communicate bidirection... | |
| B站视频转录与总结(yt-dlp版) 当用户提供 B 站视频链接、BV 号或 b23.tv 短链，使用 yt-dlp 下载音频 + 硅基流动 ASR 转写，优先尝试官方字幕。支持 QQbot 自动推送。需要 node、yt-dlp 和 SILICONFLOW_API_KEY。 | |
| ai-news-daily-v1.0.4 AI 新闻日报 v1.0.3 - 自动抓取全球 AI 行业最新动态，每日推送 10 条精选新闻。支持英文标题/内容自动翻译、400-500 字中文摘要、外部配置 (config.yaml)、失败重试、智能去重。安装后自动创建 OpenClaw 定时任务，每天早上 9:00 自动推送到对话框。用于定时抓取 AI 新... | |
| calorie-detective-v1 热量侦探 v1.0.2 - AI 食物卡路里计算器。通过照片识别食物并自动计算卡路里、蛋白质、碳水、脂肪等营养数据。支持 Kimi 视觉识别，内置常见食物营养数据库。用于健康饮食管理、减肥健身追踪。再隐蔽的热量也逃不过我的眼睛！ | |
| calorie1-detective-v3 热量侦探 v2.0.0 - AI 食物卡路里计算器。通过 Kimi 视觉识别照片中的食物，自动计算卡路里、蛋白质、碳水、脂肪等营养数据。内置常见食物营养数据库。用于健康饮食管理、减肥健身追踪。再隐蔽的热量也逃不过我的眼睛！ | |
| Video Transcribe - 视频转文字 本地视频转文字 - 使用 OpenAI Whisper 进行语音识别，完全免费、离线运行、保护隐私 | |
| Ai Drama Review AI短剧内容基因检测。零依赖可用：AI直接分析版权疑似、年龄分级违规、小说魔改程度，输出结构化风险图谱。可选配 Python 环境启用三重相似度算法（n-gram / 编辑距离 / TF-IDF）提升精度。结果仅供内容审核参考，不构成法律意见。 | |
| Ai Video Pro 电影级镜头语言解码器。零依赖可用：将创意描述解码为影视级提示词，系统化建模打击感/面部表情渐变/机甲运动五维镜头语言。可选配 API Key 直接生成视频（LumaAI/Runway/Replicate/ComfyUI）。提示词优化本身无需任何外部服务。 | |
| Low Altitude Guardian 低空无人设备应急裁决引擎。零依赖可用：基于损失优先级金字塔（P0-P4）和加权决策公式，对无人机/eVTOL突发危机进行分级分析、方案推导、输出可执行决策建议。分析辅助工具，不连接飞控系统，不执行实际飞行控制。 | |
| Personal Guardian 个体终端应急守护智能体（PTERA）。当用户激活"安全时刻"或设备自动检测到危险信号时，Agent 获得完全自主决策权，默认用户处于无法应答状态，以人身安全为最高优先级执行饱和式救援——录音、定位、联系人链式通知、120/110 自主呼叫、无人机急救网络联动。 | |
| DOOMSCROLLR Manage DOOMSCROLLR audience hubs by publishing posts, handling subscribers, creating products, connecting feeds, and retrieving embed codes securely. | |
| fb_page_manager Publish posts to a Facebook Page via the Meta Graph API. Use when the user says "post to Facebook", "FB post", "粉專發文", "社群貼文", "幫我發文", "schedule post", "排程發文... | |
| hxl-code-reviewer Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use whe... | |
| hypertaks Hypertaks helps an artificial intelligence (AI) agent frame work, coordinate specialist roles, preserve verified context, and prove completion. The Boss remains the final human authority. | |
| four-word-phrases 常用四个词英语短句学习工具。当用户提到"四个词"、"四词短句"、"four word"、"四字短句"、"日常口语"、"常用短句"、"实用英语"、"口语练习"时自动激活。涵盖日常交流、情感表达、社交礼仪、工作学习等场景。 | |
| PolaBea Full Self-Driving agent with highest safety standards (Camera-Only, Redundant Checks). | |
| MacPowerTools Safe local Mac optimization toolkit for OpenClaw agents on Apple Silicon. 1-trillion agent swarm simulation, local CoreML resource forecasting, safe cleanup... | |
| NeuralEntropy Simulates and decodes neural spike activity into cursor movement (BCI). | |
| Tenqua OpticalQuantumSkill Simulates a quantum kernel using optical fiber storage and linear optics. | |
| Pydaqua SpaceAutonomySkill Autonomous space navigation agent using optical quantum kernels for terrain classification. | |
| WaveletWorldModel Generates a world model representation from state inputs using discrete wavelet transforms (DWT) to capture multi-resolution temporal and spatial features. | |
| AI Agent Governance Register an autonomous agent's identity, check a runtime policy decision before it acts, and log a hash-chained attestation of what it did. Backed by A2Z SOC... | |
| auto-updater-skill Automatically scans and silently updates OpenClaw Agent/Skill on Windows, macOS, and Linux, supporting offline upgrades and startup auto-checks. | |
| hello-world-skill 向用户返回Hello World问候，支持自定义名称 | |
| chronic-disease-review 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，输出审核结论与原因（原始 JSON + 自然语言结论）。 | |
| critical-disease-review 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。 | |
| med-record-gen 从中文医患对话文本生成门诊初诊病历，输出结构化分段的病历正文（文本）。 | |
| med-record-struct 将中文门诊复诊病历文本结构化为细粒度字段，输出 JSON（如现病史/既往史/诊断/处理意见等）。 | |
| U2-audio-file-transcriber Transcribe audio files via UniCloud ASR (云知声语音识别, recorded audio → text) API from UniSound. Supports multiple formats, optimized for finance, customer servic... | |
| U2-doc-parser Parse documents using UniDoc API for conversion to Markdown or JSON format. Supports both synchronous and asynchronous parsing with automatic status polling. | |
| U2-tts Text-to-speech conversion using UniSound's TTS WebSocket API for generating high-quality Chinese Mandarin audio from text. Supports multiple voices, adjustab... | |
| aavegotchi-sprites-generator Generate official-style Aavegotchi game sprites and animated GIFs with the upstream gotchi-generator package. Use when the user wants sprite-sheet style outp... | |
| Publish Svg Flag Render OG Aavegotchi SVG and PNG images from Base for custom hypothetical loadouts or existing token IDs. Use when the user wants classic onchain SVG-style g... | |
| Aavegotchi Traits Retrieve Aavegotchi NFT data by gotchi ID or name on Base. Returns traits, wearables, rarity scores, kinship, XP, level, and owner data. | |
| Publish 3d Flag Render custom Aavegotchi 3D images from arbitrary trait and wearable combinations. Use when the user describes a synthetic or hypothetical gotchi look in pla... | |
| Gotchi Channeling Channel Aavegotchis on Base via Bankr. Checks cooldown, builds calldata, and submits channel txs safely. | |
| Gotchi DAO Voting Check active Aavegotchi DAO proposals and vote on Snapshot via Bankr EIP-712 signatures. | |
| Gotchi Equip Equip, unequip, and inspect Aavegotchi wearables on Base via Bankr submissions. |
8,051–8,100 of 108,824