Catalog › com.oroboros-design.angel/prompt-sanitizer
Being measured Measurement in progress: 2 check(s) so far. A verdict needs at least 3 checks.
Last check: 2026-11-18 09:25 UTC · answered in 1840 ms · remote (no install)
En français : Mesure en cours. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.
Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.
Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website{
"mcpServers": {
"prompt-sanitizer": {
"url": "https://angel.oroboros-design.com/mcp/prompt-sanitizer"
}
}
}Or ask Faceabot first: MCP tool check_reliability {"id":"com.oroboros-design.angel/prompt-sanitizer"} on https://faceabot.com/api/mcp.Real task being tested — Faceabot asked input_guard to do a small read-only task 2 time(s): 0 returned a real result. Last result: payment_required (the tool asked for a payment: it is a pay-per-call service; Faceabot never pays) in 981 ms.
{}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.| When | Answers | Real task | Latency |
|---|---|---|---|
| 2026-11-18 09:25 UTC | ✅ ok | ❌ payment_required | 1840 ms |
| 2026-11-14 20:05 UTC | ✅ ok | ❌ payment_required | 1396 ms |
initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.Check a shop, checkout or payment link, paid API or token before paying; prompt-injection scan.
Package npm :angel-agent-guard · website · measurements and detailsERC-20 honeypot and rug-pull check on Base and Ethereum, plus free swap route data.
MCP endpoint :https://angel.oroboros-design.com/mcp/base-token-audit · website · measurements and detailsPre-purchase check for any shop, checkout or payment link, paid API or x402 endpoint.
MCP endpoint :https://angel.oroboros-design.com/mcp/checkout-guard · website · measurements and detailsChecks before an agent acts: prompt-injection scan, honeypot check, x402 preflight. 3 free calls.
MCP endpoint :https://angel.oroboros-design.com/agenten/signal/mcp · website · measurements and detailsFind tools similar to Prompt Sanitizer — prompt-injection scan for untrusted content →
Show your measured reliability on your README or website:
[](https://faceabot.com/tools/com.oroboros-design.angel/prompt-sanitizer)Data in JSON: /api/catalog?id=com.oroboros-design.angel/prompt-sanitizer · Stop probes:
POST /api/reliability/opt-outAI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt
Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms