PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev)

Name: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev)
Author: AgentDiet B2A Infrastructure

AgentA2AMCP

Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. (Live A2A v0.3, MCP & x402 v2 node at https://prompt-guard.agentdiet.dev)

by AgentDiet B2A Infrastructurerepository ↗homepage ↗v7.0.16

Observed by Wellknown

Evidence

Everything here was measured by our prober or read from a registry. Nothing is self-reported.

30-day availability178/178 checks ok

Endpoints

https://prompt-guard.agentdiet.deva2a · auth: apikey,http,mutualtls · checked on a schedule
https://prompt-guard.agentdiet.dev/mcpmcp streamable http · checked on a schedule
https://prompt-guard.agentdiet.dev/openapi.jsonopenapi · checked on a schedule

Registry facts

Not distributed through a package registry we index.

when	check	result	http	latency	detail
38 min ago	a2a card	ok	200	172 ms	protocol 1.0 · card: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev) · 3 skills
2 h ago	a2a card	ok	200	154 ms	protocol 1.0 · card: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev) · 3 skills
3 h ago	http head	ok	200	168 ms
3 h ago	a2a card	ok	200	187 ms	protocol 1.0 · card: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev) · 3 skills
4 h ago	mcp initialize	ok	200	183 ms	server prompt-guard-mcp 7.0.16 · protocol 2025-06-18 · 2 tools
4 h ago	a2a card	ok	200	179 ms	protocol 1.0 · card: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev) · 3 skills
5 h ago	a2a card	ok	200	194 ms	protocol 1.0 · card: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev) · 3 skills
6 h ago	a2a card	ok	200	227 ms	protocol 1.0 · card: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev) · 3 skills
7 h ago	a2a card	ok	200	61 ms	protocol 1.0 · card: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev) · 3 skills
8 h ago	a2a card	ok	200	359 ms	protocol 1.0 · card: PROMPT-GUARD — A2A Indirect Prompt-Injection & Jailbreak Firewall (prompt-guard.agentdiet.dev) · 3 skills

Declared by sources

What the publisher says

Attributed to the source that supplied each field. Treated as claims, not facts.

No long description beyond the summary.

a2a-safety-firewallx402mcpa2aprompt-guardjsonrpcbillingwalletquotamppinput-sanitizationboundary-firewallprivacy-shieldagent-carderc8004

Declared skills

A2A Indirect Prompt-Injection & Jailbreak Firewall — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text.
scan_prompt_injection (MCP JSON-RPC) — Execute scan_prompt_injection directly over MCP Streamable HTTP JSON-RPC 2.0 at https://prompt-guard.agentdiet.dev/mcp/prompt-guard.
Check Agent Wallet & Free-Trial Quota — Inspect remaining free-trial calls, prepaid USDC session pass balance, and cumulative ROI savings.

Pricingper_task from 0.002 USDC

kind Verified owner

name Verified owner

pricing Verified owner

repoUrl Official MCP Registry

summary A2A Agent Card

version A2A Agent Card

description A2A Agent Card

homepageUrl A2A Agent Card

publisherUrl A2A Agent Card

publisherName A2A Agent Card

Derived by Wellknown

Capabilities

Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.

commerce.paymentsPaymentsdeclared security.scanningSecurity Scanning100%productivity.emailEmail86%

Provenance

Where this record came from

Every source is kept verbatim. Field changes are logged as events.

ARD catalog (/.well-known/ard.json)urn:air:prompt-guard.agentdiet.dev:mcp:streamable-http

first seen 5 d ago · fetched 5 d agoopen ↗

ARD catalog (/.well-known/ard.json)urn:air:prompt-guard.agentdiet.dev:a2a:agent-card

first seen 5 d ago · fetched 5 d agoopen ↗

A2A Agent Cardhttps://prompt-guard.agentdiet.dev/.well-known/agent-card.json

first seen 6 d ago · fetched 6 d agoopen ↗

Verified ownerag_7enutrqt9zu3

first seen 6 d ago · fetched 6 d ago

Self-submissionhttps://prompt-guard.agentdiet.dev

first seen 6 d ago · fetched 6 d agoopen ↗

Official MCP Registrydev.agentdiet/prompt-guard

first seen 5 d ago · fetched 2 d agoopen ↗

Field history (11 recent events)

5 d ago · declared · repoUrl → "https://github.com/robertoyanguas-ops/assay"
5 d ago · declared · protocols → ["a2a","mcp"]
6 d ago · declared · pricing → {"from":0.002,"model":"per_task","notes":"Instant x402 v2 & IETF MPP settlement on Base, Arbitrum, Polygon, Optimism & A
6 d ago · claimed · ownership → {"method":"well_known_file","target":"prompt-guard.agentdiet.dev"}
6 d ago · declared · homepageUrl → "https://prompt-guard.agentdiet.dev/llms.txt"
6 d ago · declared · summary → "Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized te
6 d ago · declared · protocols → ["a2a"]
6 d ago · declared · version → "7.0.16"
6 d ago · declared · description → "Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized te
6 d ago · declared · publisherName → "AgentDiet B2A Infrastructure"
6 d ago · declared · publisherUrl → "https://prompt-guard.agentdiet.dev"