app.vercel.cloakcheck-wheat/cloakcheck · v1.0.0 · agents-and-memory
app.vercel.cloakcheck-wheat/cloakcheck is healthy: it completed an MCP handshake in 763 ms and exposes 1 tools.
Scan a page for hidden prompt-injection payloads targeting AI agents.
Endpoint: https://cloakcheck-wheat.vercel.app/api/mcp (streamable-http)
No repository listed · Website · JSON · Add to my inventory
| Users (last 30 days) | 0 |
| Handshake | Healthy |
| Auth needed | None |
| Tool count | 1 |
| Latency | 763 ms |
| Last checked (UTC) | 2026-10-17T00:30:41.661Z |
| Checked (UTC) | Status | Latency | Error |
|---|---|---|---|
| 2026-10-17T00:30:41.661Z | Healthy | 763 | |
| 2026-10-15T17:40:14.994Z | Healthy | 557 | |
| 2026-10-14T16:55:44.711Z | Healthy | 2300 |
check_page_for_injection | 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 r |