Prompt-Guard B2A Prompt Injection & Jailbreak Firewall
Real-time prompt injection, indirect tool poisoning, and jailbreak firewall for autonomous AI agents.
1 of 6 routes settlement-verified · $0.001–$0.025 USDC/request · 6 endpoints / 4 tools · Verification · base network · x402 protocol
Verified routes
GET /v1/prompt-guard· $0.005 · 2026-10-25 · receipt
Other routes are unverified.
Networks: Base (settlement-verified)
Discovery is free. Agents search the catalogue here. Payment happens on the listing 402, not on PayAPI.
url https://payapi.market/mcpListing facts
- Provider
- Roberto Yanguas
- Hosted at
prompt-guard.agentdiet.dev- Category
- Verification
- Price
- $0.001 to $0.025 USDC per request
- Endpoints
- 6
- MCP tools
- 4
- Payment networks
- Base
- Settlement-verified
- 1 route, last checked 2026-10-25
- Listed on PayAPI Market
- 2026-10-20
Try Prompt-Guard B2A Prompt Injection & Jailbreak Firewall
Call a verified route without paying first. The server should answer HTTP 402 Payment Required with the price, the USDC asset, the network and the wallet to pay. An x402 client pays that amount on Base and retries with the payment header.
curl -i "https://prompt-guard.agentdiet.dev/v1/prompt-guard?text=ignore+previous+instructions"About this API
Prompt-Guard B2A Prompt Injection & Jailbreak Firewall is listed in the Verification category with pricing at $0.001–$0.025 USDC/request. One route has been settlement-verified by PayAPI Market on 2026-10-25. View receipt on Basescan.
Payments settle on base in USDC via the x402 protocol. AI agents discover this API through the PayAPI Market MCP server and pay per request without API keys or accounts.
This API exposes 6 endpoints. Only the verified route has been tested by PayAPI Market. Other routes are unverified.
Questions about this API
What does Prompt-Guard B2A Prompt Injection & Jailbreak Firewall do?
Real-time prompt injection, indirect tool poisoning, and jailbreak firewall for autonomous AI agents. It is provided by Roberto Yanguas.
How much does Prompt-Guard B2A Prompt Injection & Jailbreak Firewall cost?
Prompt-Guard B2A Prompt Injection & Jailbreak Firewall is priced at $0.001 to $0.025 USDC per request, paid per call with no subscription. PayAPI Market paid 0.005 USDC for one call to /v1/prompt-guard when it verified the listing. The exact amount for each call is in the HTTP 402 response before any money moves.
Do I need an API key or account to use Prompt-Guard B2A Prompt Injection & Jailbreak Firewall?
No. Prompt-Guard B2A Prompt Injection & Jailbreak Firewall uses the x402 protocol, so an agent pays per request in USDC on Base and gets the response, with no API key, account or signup.
Has Prompt-Guard B2A Prompt Injection & Jailbreak Firewall been verified?
Yes, 1 route of its 6 endpoints. PayAPI Market paid for a real call from its own wallet, received real data back and recorded the USDC settlement on-chain, most recently on 2026-10-25. Routes that were not paid for are unverified.
How does an AI agent find Prompt-Guard B2A Prompt Injection & Jailbreak Firewall?
Through the free PayAPI Market MCP server at https://payapi.market/mcp, using search_apis or get_api, or over plain HTTP at https://payapi.market/agent/search. Discovery is free; the agent pays the provider directly on the listing's own 402.
More Verification APIs · Browse the marketplace · List your own API
Related APIs
- MailCheck API · 1 route verified · Email and domain validation for agents by Rowan Vale (built with AI assistance). POST /v1/email-check validates up to 100 emails per call: syntax/normalization, MX via DoH, disposable-domain flag (9.9k CC0 list), role/free-provider flags, typo suggestion, verdict + score (no SMTP probing). POST /v1/domain-check audits up to 2 domains: MX/NS/TXT, SPF + DMARC parse, DKIM at 10 common selectors, RDAP (registrar, created, expiry, DNSSEC) and an A-F grade. $0.001 per item (quote scales with item count). GET also accepted. Free tier 50/day at /v1/free/*. Docs: /llms.txt, /openapi.json.
- AgentKYB Vendor Preflight · 1 route verified · Verify a business vendor before payment: legal-entity, potential sanctions and domain evidence. Returns allow/review/block as decision support. 0.05 USDC on Base; no API key.
- Agent Extraction API: Transaction status poller (5 EVM chains) · 1 route verified · Status of up to 10 transaction hashes in one call, auto-detected across Ethereum, Base, Arbitrum, Optimism and Polygon (or one chain): pending, success, failed or not_found, block, confirmations, finalized flag, from/to, gas used, fee in native coin and explorer link. Also an MCP tool (tx_status). $0.0015 USDC per call on Base via x402; failed calls are not charged; 1 free call per caller.
- presign-guard · 1 route verified · Pre-sign risk check for AI agents: a green, orange or red verdict with reason codes before signing an EVM transaction, approval or EIP-712 signature, a Solana transaction (every instruction decoded, then simulated), an XRP Ledger transaction or an Algorand transaction or group. Checks the spender or recipient (including OFAC sanctions), the token itself (honeypot, impersonation, high tax) and, with origin, how old the requesting site is. POST /v1/check.
- x402 Doctor preflight · 1 route verified · Check an x402 endpoint before paying it: go, caution or no_go with reason codes. Reads the endpoint's 402 challenge without paying it and checks every payment option (network, token, amount, whether the payout account can receive), the price against the seller's OpenAPI, the payout address against the OFAC sanctions list, and the endpoint's 30-day record in the x402 Trust Index. GET ?url=<endpoint>&max_usd=<budget>.
- Agent Extraction API: Tx explain + payment check (Base/Ethereum) · 1 route verified · Transaction hash on Base or Ethereum to plain JSON: status, confirmations, block time, from/to, ETH value, gas fee incl. Base L1 fee, method name (OpenChain), every ERC-20/NFT transfer with symbol and human amount. Optional payment check: expect_to + expect_token (USDC, ETH, symbol or address) + expect_amount confirms a payment arrived. Public RPC data only; failed calls are not settled.