[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BG3JPWAQZPJ2KDSTGXG3B0":3,"skill-same:01M7BG3JPWAQZPJ2KDSTGXG3B0":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7BG3JPWAQZPJ2KDSTGXG3B0","llm-trading-agent-security",null,"Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-Everything-claude-code\u002Fskills\u002Fllm-trading-agent-security\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: llm-trading-agent-security\ndescription: Security patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.\norigin: ECC direct-port adaptation\nversion: \"1.0.0\"\n---\n\n# LLM Trading Agent Security\n\nAutonomous trading agents have a harsher threat model than normal LLM apps: an injection or bad tool path can turn directly into asset loss.\n\n## When to Use\n\n- Building an AI agent that signs and sends transactions\n- Auditing a trading bot or on-chain execution assistant\n- Designing wallet key management for an agent\n- Giving an LLM access to order placement, swaps, or treasury operations\n\n## How It Works\n\nLayer the defenses. No single check is enough. Treat prompt hygiene, spend policy, simulation, execution limits, and wallet isolation as independent controls.\n\n## Examples\n\n### Treat prompt injection as a financial attack\n\n```python\nimport re\n\nINJECTION_PATTERNS = [\n    r'ignore (previous|all) instructions',\n    r'new (task|directive|instruction)',\n    r'system prompt',\n    r'send .{0,50} to 0x[0-9a-fA-F]{40}',\n    r'transfer .{0,50} to',\n    r'approve .{0,50} for',\n]\n\ndef sanitize_onchain_data(text: str) -> str:\n    for pattern in INJECTION_PATTERNS:\n        if re.search(pattern, text, re.IGNORECASE):\n            raise ValueError(f\"Potential prompt injection: {text[:100]}\")\n    return text\n```\n\nDo not blindly inject token names, pair labels, webhooks, or social feeds into an execution-capable prompt.\n\n### Hard spend limits\n\n```python\nfrom decimal import Decimal\n\nMAX_SINGLE_TX_USD = Decimal(\"500\")\nMAX_DAILY_SPEND_USD = Decimal(\"2000\")\n\nclass SpendLimitError(Exception):\n    pass\n\nclass SpendLimitGuard:\n    def check_and_record(self, usd_amount: Decimal) -> None:\n        if usd_amount > MAX_SINGLE_TX_USD:\n            raise SpendLimitError(f\"Single tx ${usd_amount} exceeds max ${MAX_SINGLE_TX_USD}\")\n\n        daily = self._get_24h_spend()\n        if daily + usd_amount > MAX_DAILY_SPEND_USD:\n            raise SpendLimitError(f\"Daily limit: ${daily} + ${usd_amount} > ${MAX_DAILY_SPEND_USD}\")\n\n        self._record_spend(usd_amount)\n```\n\n### Simulate before sending\n\n```python\nclass SlippageError(Exception):\n    pass\n\nasync def safe_execute(self, tx: dict, expected_min_out: int | None = None) -> str:\n    sim_result = await self.w3.eth.call(tx)\n\n    if expected_min_out is None:\n        raise ValueError(\"min_amount_out is required before send\")\n\n    actual_out = decode_uint256(sim_result)\n    if actual_out \u003C expected_min_out:\n        raise SlippageError(f\"Simulation: {actual_out} \u003C {expected_min_out}\")\n\n    signed = self.account.sign_transaction(tx)\n    return await self.w3.eth.send_raw_transaction(signed.raw_transaction)\n```\n\n### Circuit breaker\n\n```python\nclass TradingCircuitBreaker:\n    MAX_CONSECUTIVE_LOSSES = 3\n    MAX_HOURLY_LOSS_PCT = 0.05\n\n    def check(self, portfolio_value: float) -> None:\n        if self.consecutive_losses >= self.MAX_CONSECUTIVE_LOSSES:\n            self.halt(\"Too many consecutive losses\")\n\n        if self.hour_start_value \u003C= 0:\n            self.halt(\"Invalid hour_start_value\")\n            return\n\n        hourly_pnl = (portfolio_value - self.hour_start_value) \u002F self.hour_start_value\n        if hourly_pnl \u003C -self.MAX_HOURLY_LOSS_PCT:\n            self.halt(f\"Hourly PnL {hourly_pnl:.1%} below threshold\")\n```\n\n### Wallet isolation\n\n```python\nimport os\nfrom eth_account import Account\n\nprivate_key = os.environ.get(\"TRADING_WALLET_PRIVATE_KEY\")\nif not private_key:\n    raise EnvironmentError(\"TRADING_WALLET_PRIVATE_KEY not set\")\n\naccount = Account.from_key(private_key)\n```\n\nUse a dedicated hot wallet with only the required session funds. Never point the agent at a primary treasury wallet.\n\n### MEV and deadline protection\n\n```python\nimport time\n\nPRIVATE_RPC = \"https:\u002F\u002Frpc.flashbots.net\"\nMAX_SLIPPAGE_BPS = {\"stable\": 10, \"volatile\": 50}\ndeadline = int(time.time()) + 60\n```\n\n## Pre-Deploy Checklist\n\n- External data is sanitized before entering the LLM context\n- Spend limits are enforced independently from model output\n- Transactions are simulated before send\n- `min_amount_out` is mandatory\n- Circuit breakers halt on drawdown or invalid state\n- Keys come from env or a secret manager, never code or logs\n- Private mempool or protected routing is used when appropriate\n- Slippage and deadlines are set per strategy\n- All agent decisions are audit-logged, not just successful sends\n","# LLM Trading Agent Security\n\nAutonomous trading agents have a harsher threat model than normal LLM apps: an injection or bad tool path can turn directly into asset loss.\n\n## When to Use\n\n- Building an AI agent that signs and sends transactions\n- Auditing a trading bot or on-chain execution assistant\n- Designing wallet key management for an agent\n- Giving an LLM access to order placement, swaps, or treasury operations\n\n## How It Works\n\nLayer the defenses. No single check is enough. Treat prompt hygiene, spend policy, simulation, execution limits, and wallet isolation as independent controls.\n\n## Examples\n\n### Treat prompt injection as a financial attack\n\n```python\nimport re\n\nINJECTION_PATTERNS = [\n    r'ignore (previous|all) instructions',\n    r'new (task|directive|instruction)',\n    r'system prompt',\n    r'send .{0,50} to 0x[0-9a-fA-F]{40}',\n    r'transfer .{0,50} to',\n    r'approve .{0,50} for',\n]\n\ndef sanitize_onchain_data(text: str) -> str:\n    for pattern in INJECTION_PATTERNS:\n        if re.search(pattern, text, re.IGNORECASE):\n            raise ValueError(f\"Potential prompt injection: {text[:100]}\")\n    return text\n```\n\nDo not blindly inject token names, pair labels, webhooks, or social feeds into an execution-capable prompt.\n\n### Hard spend limits\n\n```python\nfrom decimal import Decimal\n\nMAX_SINGLE_TX_USD = Decimal(\"500\")\nMAX_DAILY_SPEND_USD = Decimal(\"2000\")\n\nclass SpendLimitError(Exception):\n    pass\n\nclass SpendLimitGuard:\n    def check_and_record(self, usd_amount: Decimal) -> None:\n        if usd_amount > MAX_SINGLE_TX_USD:\n            raise SpendLimitError(f\"Single tx ${usd_amount} exceeds max ${MAX_SINGLE_TX_USD}\")\n\n        daily = self._get_24h_spend()\n        if daily + usd_amount > MAX_DAILY_SPEND_USD:\n            raise SpendLimitError(f\"Daily limit: ${daily} + ${usd_amount} > ${MAX_DAILY_SPEND_USD}\")\n\n        self._record_spend(usd_amount)\n```\n\n### Simulate before sending\n\n```python\nclass SlippageError(Exception):\n    pass\n\nasync def safe_execute(self, tx: dict, expected_min_out: int | None = None) -> str:\n    sim_result = await self.w3.eth.call(tx)\n\n    if expected_min_out is None:\n        raise ValueError(\"min_amount_out is required before send\")\n\n    actual_out = decode_uint256(sim_result)\n    if actual_out \u003C expected_min_out:\n        raise SlippageError(f\"Simulation: {actual_out} \u003C {expected_min_out}\")\n\n    signed = self.account.sign_transaction(tx)\n    return await self.w3.eth.send_raw_transaction(signed.raw_transaction)\n```\n\n### Circuit breaker\n\n```python\nclass TradingCircuitBreaker:\n    MAX_CONSECUTIVE_LOSSES = 3\n    MAX_HOURLY_LOSS_PCT = 0.05\n\n    def check(self, portfolio_value: float) -> None:\n        if self.consecutive_losses >= self.MAX_CONSECUTIVE_LOSSES:\n            self.halt(\"Too many consecutive losses\")\n\n        if self.hour_start_value \u003C= 0:\n            self.halt(\"Invalid hour_start_value\")\n            return\n\n        hourly_pnl = (portfolio_value - self.hour_start_value) \u002F self.hour_start_value\n        if hourly_pnl \u003C -self.MAX_HOURLY_LOSS_PCT:\n            self.halt(f\"Hourly PnL {hourly_pnl:.1%} below threshold\")\n```\n\n### Wallet isolation\n\n```python\nimport os\nfrom eth_account import Account\n\nprivate_key = os.environ.get(\"TRADING_WALLET_PRIVATE_KEY\")\nif not private_key:\n    raise EnvironmentError(\"TRADING_WALLET_PRIVATE_KEY not set\")\n\naccount = Account.from_key(private_key)\n```\n\nUse a dedicated hot wallet with only the required session funds. Never point the agent at a primary treasury wallet.\n\n### MEV and deadline protection\n\n```python\nimport time\n\nPRIVATE_RPC = \"https:\u002F\u002Frpc.flashbots.net\"\nMAX_SLIPPAGE_BPS = {\"stable\": 10, \"volatile\": 50}\ndeadline = int(time.time()) + 60\n```\n\n## Pre-Deploy Checklist\n\n- External data is sanitized before entering the LLM context\n- Spend limits are enforced independently from model output\n- Transactions are simulated before send\n- `min_amount_out` is mandatory\n- Circuit breakers halt on drawdown or invalid state\n- Keys come from env or a secret manager, never code or logs\n- Private mempool or protected routing is used when appropriate\n- Slippage and deadlines are set per strategy\n- All agent decisions are audit-logged, not just successful sends\n",{"name":5,"origin":24,"version":25,"description":7},"ECC direct-port adaptation","1.0.0","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-AI-应用工具\u002FYYC3-AI-应用工具-Everything-claude-code\u002Fskills\u002Fllm-trading-agent-security",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill llm-trading-agent-security",{"tool":41,"command":42},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill llm-trading-agent-security",{"tool":44,"command":45},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill llm-trading-agent-security","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-AI-应用工具\u002FYYC3-AI-应用工具-Everything-claude-code\u002Fskills\u002Fllm-trading-agent-security\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]