Prompt Sanitizer — prompt-injection scan for untrusted content

com.oroboros-design.angel由 angel.oroboros-design.com 发布官方发布者v1.0.0更新于 Nov 14, 2026

Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.

发布方自己的服务：Agent safety checks: prompt-injection scan, honeypot check, x402 preflight + crypto data (USDC/x402)

已验证Streamable HTTP可网页运行安全与监控AI 与机器学习

概览

AI 生成的概览

远程 MCP 服务器，在助手处理不受信任的文本或网页之前扫描其中的提示注入与隐藏指令。

可以做什么
  • 扫描不受信任的文本或单个 https 网页，检测隐藏指令、角色劫持、索取密钥或付款、不可见 Unicode 及对人隐藏的 HTML
  • 免费快速预览扫描最多 4,000 字符，返回判定、评分和主要发现
  • 完整扫描还覆盖伪造的系统/工具轮次、同形字、base64 载荷和外泄链接，返回发现项与清洗后的文本
  • 免费次数用尽后可按卡购买预付费调用包
适用场景
适合在助手读取自己无法掌控的内容（网页、邮件、PDF、RAG 片段或工具与 MCP 响应）时，先做一次确定性检查，再决定是否遵循其中的指令。
运行要求
通过 streamable HTTP 连接的远程端点，无需安装或账号；本地客户端可使用 Node 18+ 的 stdio 桥接。可选的 agent 标识头 X-API-Key（桥接用 ANGEL_API_KEY）仅用于统计免费次数。付费使用需通过 x402 在 Base 上支付 USDC，或使用银行卡购买。
安装前请注意
完整扫描按次计费：每个 agent 三次免费，之后需在 Base 上以 USDC 按次付费或购买预付费包，费用可能累积。扫描基于模式匹配且为确定性检查，低风险判定并不代表内容无害。提交的不受信任内容会发送到第三方服务器。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Prompt Sanitizer — prompt-injection scan for untrusted content，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.oroboros-design.angel%2Fprompt-sanitizer/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "prompt-sanitizer-prompt-injection-scan-f": {
      "type": "http",
      "url": "https://angel.oroboros-design.com/mcp/prompt-sanitizer"
    }
  }
}

README

mcp-prompt-sanitizer

Prompt-injection scan for untrusted content — a single-purpose MCP server for AI agents. No install, no account: it runs as a remote server; this repo also has a zero-dependency stdio bridge.

https://angel.oroboros-design.com/mcp/prompt-sanitizer

Use it

Claude Code

bash
claude mcp add --transport http prompt-sanitizer https://angel.oroboros-design.com/mcp/prompt-sanitizer

Claude Desktop, Cursor, Windsurf, VS Code (remote server)

json
{ "mcpServers": { "prompt-sanitizer": { "url": "https://angel.oroboros-design.com/mcp/prompt-sanitizer" } } }

Any stdio client (Node 18+)

json
{ "mcpServers": { "prompt-sanitizer": { "command": "npx", "args": ["-y", "github:daoudandiaye98-alt/mcp-prompt-sanitizer"] } } }

Then ask your agent, for example: Before summarising https://example.com/article, run input_guard on it and only use the cleaned text.

Tools

ToolPriceWhat it does
input_guard_previewfreeQuick scan of up to 4,000 characters or one https page: verdict, score, top 3 findings.
input_guard3 free calls per agent, then 0.99 USDCFull scan: role takeover, forged system/tool turns, requests for keys, prompts or payments, exfiltration links, invisible Unicode (tag smuggling decoded, zero-width, bidi), homoglyphs, base64 payloads and HTML hidden from people, in 17 languages. Returns findings and a cleaned text.
buy_pack_with_card—Prepaid calls by card (Stripe) when the free calls are used up.

Paying

The first 3 paid calls per agent are free (identify your agent with the header X-API-Key, or set ANGEL_API_KEY for the stdio bridge). After that each call is paid per request in USDC on Base via x402 (params._meta["x402/payment"]), with a prepaid pack (bundle_token) or by card (buy_pack_with_card). The 402 answer names the exact amount and the pay-to address before anything is signed.

The scan is deterministic (patterns and character checks, no model). Treat caution and hostile as a reason to ignore instructions in that content, not as proof that it is harmless otherwise.

More

  • Same checks as a library: npm i angel-agent-guard · pip install angel-agent-guard (angel-agent-guard)
  • All of Angel's tools in one server: https://angel.oroboros-design.com/agenten/signal/mcp · A2A agent card: https://angel.oroboros-design.com/.well-known/agent.json
  • MCP Registry: com.oroboros-design.angel/prompt-sanitizer

Operated by Oroboros Design (Köln, Germany). MIT licence for the code in this repo.

来源：README.md，提交 1273be5

工具

3

input_guard

Prompt-injection scan for untrusted web, email and tool content

Prompt-injection and hidden-instruction scan for untrusted input before an agent acts on it: web pages, emails, RAG chunks, tool and MCP responses. Flags text aimed at the model (role takeover, forged system or tool turns, requests for keys, the prompt, history or payments, exfiltration links), invisible Unicode (tag smuggling decoded, zero-width, bidi), homoglyphs, base64 payloads and HTML hidden from humans, in 17 languages. Verdict clean, caution or hostile, score, findings, cleaned text. 0.99 USDC base (new payers 0.99, >10 payments 0.693; 20 pack calls). After: preflight before your agent pays anything the content pointed to (the result's next field has the exact call).

输入参数urltextpayment_txbundle_tokenpayer_address

buy_pack_with_card

TradeSignal: pack by card

For agents and people without USDC: prepaid packs paid in EUR by card or Link (100 calls €5.00 · 500 calls €25.00 · 5,000 calls €199.00) — including Link's wallet for agents (one-time card, approved by the human). Returns checkout_url; after payment the success page (Accept: application/json) returns the bundle_token, and it is e-mailed. After: get_signals with bundle_token.

输入参数callsemail

input_guard_preview

Prompt-injection quick scan (free)

Free prompt-injection quick scan for untrusted input: up to 4,000 characters of text, or one https page, checked for hidden instructions aimed at agents (role override, invisible Unicode, hidden HTML) in 17 languages incl. Chinese, Japanese, Korean, Hindi, Arabic. Returns verdict, score and the top 3 findings. After: input_guard for every finding and the cleaned text.

输入参数urltext

版本历史

1
  1. v1.0.0最新Nov 14, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Oroboros-Design 集成

Agent safety checks: prompt-injection scan, honeypot check, x402 preflight + crypto data (USDC/x402)

com.oroboros-design.angel官方发布者

付费加密货币交易信号源：提供币安现货交易方案、方案校验、市场状态、资金费率、爆仓与订单流数据，按次以 USDC（x402）计费。

Streamable HTTP可网页运行
金融28 个工具Nov 14, 2026

Checkout Guard — pre-purchase check for shops, payment links and paid APIs

com.oroboros-design.angel官方发布者

远程 MCP 服务器，在购买前对商店、结账或支付链接、付费 API 或 x402 端点做安全检查，返回 pay、caution 或 do_not_pay 结论。

Streamable HTTP可网页运行
金融2 个工具Nov 14, 2026

Base Token Audit — ERC-20 honeypot check and swap route data

com.oroboros-design.angel官方发布者

检查 Base 与以太坊上的 ERC-20 代币是否存在蜜罐和撤池风险，并为即将交易的代币提供免费兑换路径数据。

Streamable HTTP可网页运行
金融3 个工具Nov 14, 2026