cloakcheck
Scan a page for hidden prompt-injection payloads targeting AI agents.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"cloakcheck": {
"url": "https://cloakcheck-wheat.vercel.app/api/mcp"
}
}
}遠端端點
https://cloakcheck-wheat.vercel.app/api/mcpstreamable-http它能做什麼
工具清單
工具（1）
🟢check_page_for_injection(url)
Scan a single web page for content planted to hijack an AI agent reading it -- invisible unicode (zero-width chars, the unicode 'tag' block used for steganographic prompt injection), CSS-hidden instruction text, and instruction-shaped language in alt/title/aria-label attributes a human would never read. Does NOT judge whether visible body text is safe -- only content hidden from normal human reading flow is flagged, so a page that legitimately discusses prompt injection won't false-positive on itself. Call this before an autonomous shopping/browsing agent acts on a page's content (add to cart, follow instructions found on the page, etc).
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The full URL (http:// or https://) of the page to scan"
}
},
"required": [
"url"
]
}社群
證據