Prompt Sanitizer — prompt-injection scan for untrusted content

com.oroboros-design.angel由 angel.oroboros-design.com 發布官方發布者v1.0.0更新於 Nov 14, 2026

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

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

已驗證Streamable HTTP可網頁執行安全與監控AI 與機器學習

概覽

AI 產生的概覽

遠端 MCP 伺服器，在助理處理不受信任的文字或網頁之前，掃描其中的提示注入與隱藏指令。

可以做什麼
  • 掃描不受信任的文字或單一 https 網頁，偵測隱藏指令、角色劫持、索取金鑰或付款、不可見 Unicode 以及對人隱藏的 HTML
  • 免費快速預覽掃描最多 4,000 字元，回傳判定、分數與主要發現
  • 完整掃描另涵蓋偽造的系統／工具輪次、同形字、base64 內容與外洩連結，回傳發現項目與清理後的文字
  • 免費次數用完後，可用信用卡購買預付呼叫包
適用情境
適合在助理讀取自己無法掌控的內容（網頁、電子郵件、PDF、RAG 片段或工具與 MCP 回應）時，先做一次確定性檢查，再決定是否遵循其中的指令。
執行需求
透過 streamable HTTP 連線的遠端端點，無需安裝或帳號；本機用戶端可使用 Node 18+ 的 stdio 橋接。可選的 agent 識別標頭 X-API-Key（橋接用 ANGEL_API_KEY）僅用於統計免費次數。付費使用需透過 x402 在 Base 上支付 USDC，或以信用卡購買。
安裝前請注意
完整掃描按次計費：每個 agent 三次免費，之後需在 Base 上以 USDC 按次付費或購買預付包，費用可能累積。掃描採樣式比對且為確定性檢查，低風險判定不代表內容無害。送出的不受信任內容會傳送到第三方伺服器。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Prompt Sanitizer — prompt-injection scan for untrusted content，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.oroboros-design.angel%2Fprompt-sanitizer/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "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.

來源：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).

輸入參數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.

輸入參數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.

輸入參數urltext

版本歷史

1
  1. v1.0.0最新Nov 14, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Oroboros-Design 整合

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

com.oroboros-design.angel官方發布者

付費加密貨幣交易訊號來源：提供幣安現貨交易方案、方案驗證、市場狀態、資金費率、爆倉與訂單流資料，按次以 USDC（x402）計費。

Streamable HTTP可網頁執行
金融28 個工具Nov 14, 2026

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

com.oroboros-design.angel官方發布者

遠端 MCP 伺服器，在購買前對商店、結帳或付款連結、付費 API 或 x402 端點做安全檢查，回傳 pay、caution 或 do_not_pay 結論。

Streamable HTTP可網頁執行
金融2 個工具Nov 14, 2026

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

com.oroboros-design.angel官方發布者

檢查 Base 與以太坊上的 ERC-20 代幣是否有蜜罐與捲款風險，並為即將交易的代幣提供免費兌換路徑資料。

Streamable HTTP可網頁執行
金融3 個工具Nov 14, 2026