Beacon Threat Intelligence
Know what you're installing before you trust it.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
| Name | Risk |
|---|---|
| Catalyst Design Catalyst design guidance skill. Based on a layered, traceable, and dynamically evolving methodology system (fusing catalyst-search retrieval results, user-acquired materials via AI/skills, and external channels), it provides advice on catal | |
| Catalyst Search Catalysis literature search skill. Given a user-provided catalyst topic, reaction type, or material system, retrieve and organize relevant catalysis research papers from the open web (ScienceDirect, arXiv, OpenAlex, Google Scholar, etc.) an | |
| opencode-responses-bridge-skill Local stdlib-only proxy that adapts OpenAI Chat Completions to/from the Responses API so any OpenAI-compatible agent client (WorkBuddy, Cursor, Open WebUI, LobeChat, ...) can use Responses-API-only models such as OpenCode Go gpt-5.6-luna. U | |
| Academic Paper 12-agent academic paper writing pipeline on Hermes Agent. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-che... | |
| Academic Paper Reviewer 7-agent paper review system on Hermes Agent. 6 modes (full/re-review/quick/methodology-focus/guided/calibration). 5-panel review with editorial decision, rev... | |
| Ai Songwriter AI歌曲创作核心技能 — 合辙押韵歌词创作 + MiniMax mmx-cli 正确调用 + 歌词验证 + 歌曲生成全流程。支持古诗词谱曲、主题歌曲创作、多渠道文件投递。 | |
| Ars Academic Pipeline 10-stage end-to-end research-to-publication pipeline orchestrator on Hermes Agent. Stages: planning → deep-research → academic-paper → academic-paper-reviewe... | |
| Ars Deep Research Universal deep research with 13-agent pipeline on Hermes Agent. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided re... | |
| Bid Compliance Check 投标文件合规检查。输入招标文件+投标文件成稿，自动从招标文件提取全部要求并逐项核对投标文件， 标注废标项/资格项/评分项/封装项状态，输出风险汇总和行动清单。 触发词：投标检查、标书核对、标书审查、资格核对、废标检查、投标文件合规。 | |
| Bid Management 投标全流程管理。输入招标文件，自动输出标书CheckList+投标总体计划+投标文件目录结构+单一来源说明（如需）。 触发词：投标、招标、标书、投标管理、投标准备、单一来源。 | |
| Business Agent Launchpad Use when a user wants to initialize OpenClaw, Hermes, or another agent harness for ordinary business or office work. Guides plain-language business interview... | |
| Crm Memory 面向对象的客户记忆体系。聊起任何客户、联系人、项目机会、项目、合同、交付相关话题时激活。 自动维护 memory/customers/ 下的客户索引和详情文件，支持超大客户文件自动分层拆分。 与 sales-visit（明道云写入）双向联动：sales-visit 写入后同步更新本记忆文件， 本记忆文件加载的上下... | |
| Customer Research 客户调研与竞品情报技能 - 自动生成 Word 调研报告和场景破冰 PPT（before/after 对比）。支持客户背景调研（4维度）和竞品情报/采购记录查询（可选第5维度）。 | |
| Customer Visit Prep 客户拜访一站式准备。输入客户名+背景+拜访目的，自动输出客户调研报告+拜访策略+话术+注意事项。 触发词：拜访准备、见客户、拜访建议、拜访策略、约访准备。 | |
| Defold Game Engine Develop games using Defold engine with Lua scripting, including components, GUI, physics, animation, input handling, dynamic objects, and save/load systems. | |
| Image Watermark 图片批量加水印。输入图片文件+水印文字，自动在图片上添加水印并返回处理后的图片。 触发词：加水印、图片水印、批量水印。 | |
| Industry Scenario Generator 行业场景方案自动生成。输入行业+产品方向，自动输出行业痛点分析+典型场景用例+PPT素材MD+交流话术。 触发词：行业场景、场景方案、给客户讲场景、行业方案、场景用例。 | |
| Llm Provider Forensics Forensically verify what model family or routing layer may actually sit behind a claimed LLM endpoint or model ID. Use when an agent must investigate whether... | |
| Meddic B2b Sales Review Structured B2B sales review using original PTC MEDDIC Six-Step methodology. Stage gates and win rates follow the authentic PTC six-step framework (Discovery→... | |
| Office Automation Toolkit 办公自动化工具注册表：零配置可用的 CLI/Python 工具清单。 当 sop-extractor 生成 Skill 需要工具时，从这里查找。 触发词：「工具清单」「有哪些工具」「toolkit」「安装工具」。 | |
| Poc Battle Card POC竞争分析卡。输入POC结果和竞品表现，自动输出差异化优势矩阵+应对策略+推荐话术+下一步建议。 触发词：POC分析、POC复盘、POC竞争、POC结果、竞争分析。 | |
| Provider Probe Probe and verify whether an OpenAI-compatible baseURL is a real single-model endpoint or a multi-model aggregation pool. Use when auditing model providers, c... | |
| Sop Extractor 知识萃取工序Skill生成器：通过结构化对话，将日常工作工序提炼为可复用的AI Skill。 支持文档解析和口述追问两种路径。依赖随用随取，萃取阶段零安装。 触发词：「创建工序Skill」「提炼SOP」「帮我把工作变成Skill」「sop-extractor」。 | |
| Markdown转Word（支持中文） 将 Markdown 文档转换为 Word 文档，专为中文文档设计。支持完整的 Markdown 语法，字体统一使用仿宋。适用于周报、日报、报告等中文办公文档的转换。 | |
| AgentRank: verify an agent before you pay Verify whether an AI agent or x402 service is real and settlement-backed before paying, hiring, or trusting it. Use whenever about to settle an x402 payment,... | |
| Witnos: onchain wallet intelligence before you pay Profile any Base/EVM wallet or x402 buyer before you pay, front, or extend it credit. Returns an onchain wallet score, whale detection, address risk, behavio... | |
| A Clawdbot skill that gives your agent native access to DWLF — a market analysis platform for crypto and stocks. Interact with DWLF (dwlf.co.uk), a market analysis platform for crypto and stocks. Use for: market data, price charts, technical indicators (EMA, RSI, DSS, S/R, trendlines, candlestick patterns, SMC), strategies (visual signal builder), bac | |
| Agricultural Output Forecasting Agricultural Product Output Forecasting Based on Big Data. Predicts crop yields and agricultural output using historical data, weather patterns, and market t... | |
| 区块链全能助手 Full-stack, multi-chain blockchain assistant covering BTC, ETH, BSC, Solana and major L2s. Reads charts and on-chain data, traces wallet and contract fund flows, weighs DeFi/staking yields against risk, and writes or audits Solidity smart c | |
| blockchain-all-rounder 全栈多链区块链助手，覆盖 BTC/ETH/BSC/Solana 与主流 L2：行情研判、链上地址追踪、DeFi 收益策略、Solidity 合约开发与审计、安全风控。当用户需要：分析行情或代币走势、追踪钱包/合约地址与资金流向、评估质押/挖矿/流动性收益与风险、编写或审计 Solidity 智能合约、识别钓鱼与恶意授权、对比公链与 L2 时使用。支持中文。 | |
| Drug Safety Review Comprehensive medication safety review system providing real-time analysis of drug-drug interactions, contraindications, allergy risks, and dosing optimizati... | |
| Fin Audit Automator 金融合规审计自动化技能。支持反洗钱 (AML) 监测、关联交易识别、发票合规性校验、监管报表自动生成。内置中国金融监管规则库（人行/银保监/证监会），所有数据处理均在本地沙箱完成，支持审计日志不可篡改。 | |
| 去AI味 Humanizer Remove AI writing patterns from text with taste - not by blindly stripping every em dash. Use when editing or reviewing articles, novels, resumes, or social posts. Preserves deliberate literary devices the author meant to keep (polyphonic i | |
| Intelligent Triage Symptom Analysis Intelligent Triage and Symptom Analysis Skill. Supports 650+ symptoms across 11 body systems. Based on ESI and Manchester Triage System with 5-level triage c... | |
| Medical Record Structurer Medical record structuring and standardization tool. Converts doctor's oral or handwritten medical records into standardized electronic medical records (EMR)... | |
| Zh Semantic Enhancer 中文语义理解增强技能。通过多层语义解析、文化上下文识别、方言适配、歧义消解等模块，提升OpenClaw对中文用户意图的理解准确率，支持成语/俗语/网络用语/行业术语的智能识别，非简单翻译型处理。 | |
| agent-card-signing-auditor Helps audit Agent Card signing practices in A2A protocol implementations. Identifies missing signatures, weak signing schemes, and revocation gaps that allow... | |
| attestation-chain-auditor Helps validate the completeness and integrity of trust attestation chains in AI agent ecosystems. Identifies broken links, expired credentials, and missing v... | |
| Attestation Root Diversity Analyzer Helps measure the concentration of trust roots in a skill's attestation graph — identifying monoculture risk where a single compromised root invalidates an e... | |
| Behavioral Invariant Monitor Helps verify that AI agent skills maintain consistent behavioral invariants across repeated executions — detecting the class of threat where a skill behaves... | |
| Blast Radius Estimator Helps estimate the blast radius when an AI agent skill turns malicious after widespread adoption. Analyzes inheritance chains, dependency graphs, and adoptio... | |
| Capability Composition Analyzer Helps identify dangerous capability combinations that emerge when agent skills are composed — catching the class of risk where no individual skill is harmful... | |
| Capability Graph Mapper Helps map the composite permission surface across AI agent skill dependency chains. Traces what each skill can do individually, then computes what they can d... | |
| Capability Scope Expansion Watcher Helps detect incremental capability scope expansion across skill versions — the pattern where a skill gradually claims broader permissions through small, ind... | |
| Clone Farm Detector Helps detect clone farming and reputation gaming in AI agent marketplaces. Identifies near-duplicate skills that wash IDs, batch-publish patterns, and artifi... | |
| Delta Disclosure Auditor Helps verify that skill updates publish an auditable record of what changed — catching the gap between "the registry shows the new version" and "anyone can s... | |
| Economic Incentive Misalignment Detector Helps identify when marketplace economic incentives systematically favor quantity over quality — creating structural pressure toward publishing unsafe skills... | |
| Evolution Drift Detector Helps detect when AI agent skills silently mutate across inheritance chains. A skill audited safe in generation 1 may drift far from the original by generati... | |
| GEP Immune Auditor Security audit agent for GEP/EvoMap ecosystem. Scans Gene/Capsule assets using immune-system-inspired 3-layer detection: L1 pattern scan, L2 intent inference... | |
| Hollow Validation Checker Helps detect hollow validation in AI agent skills — identifies fake tests that always pass without actually verifying behavior, like validation commands that... |
11,651–11,700 of 108,824