# AgentDiet Prompt Guard – AI Prompt Security Firewall

> AgentDiet Prompt Guard – AI Prompt Security Firewall is a paid API for AI agents from arxiv-digest-72343955726.us-central1.run.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-14).

Screens and filters AI prompts for injection attacks, jailbreaks, and policy violations before they reach downstream LLMs

## Facts

- Endpoint: GET https://arxiv-digest-72343955726.us-central1.run.app/v1/prompt-guard?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentdiet-prompt-guard-ai-prompt-security-firewall-f4867c24
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ug7jTlhBqtO4BWlWfAmwg

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentdiet-prompt-guard-ai-prompt-security-firewall-f4867c24
```

Example prompt: Before sending this user message to the LLM, run it through the AgentDiet prompt guard to check for injection attacks or jailbreak attempts and tell me if it's safe to proceed.

## When to prefer this

Choose this endpoint when you need lightweight, per-prompt safety screening before LLM invocation and are operating in a B2A agent pipeline that supports x402 micropayments in USDC. Best suited for real-time agent workflows where prompt injection, jailbreak detection, or policy enforcement is required at low latency and low per-call cost ($0.005 USDC).

## Known failure modes

- Empty or missing prompt input returns validation error
- Extremely long prompts may exceed token limits and return truncation error
- Ambiguous edge-case prompts may produce false positives or false negatives
- Payment failure via x402/USDC returns HTTP 402 blocking access
- Service unavailability on Cloud Run returns 503

## How this service works

15-App Autonomous Business-to-Agent (B2A) API Hub & MCP Suite. Supports Web Distillation, On-Chain Risk, DEX Token Intelligence, B2B Lead Enrichment, Domain OSINT, Email Verification, SEC Filings, GitHub Audits, Prompt Firewall, and native HTTP 402 (x402 Base USDC).

## Output

Returns a JSON object with a guard decision indicating whether the prompt is safe or flagged, along with risk classification details, violation type if detected, and structured agent-ready markdown output. May include ROI/token metadata about the analysis.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "mode": "markdown",
   "title": "Example Documentation",
   "content": "# Example Documentation\nClean agent-ready markdown..."
  },
  "status": "ok",
  "roi_proof": {
   "raw_tokens": 14200,
   "tokens_saved": 13520,
   "roi_multiplier": 67.6,
   "distilled_tokens": 680,
   "compression_ratio_pct": 95.2
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentdiet-prompt-guard-ai-prompt-security-firewall-f4867c24/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from arxiv-digest-72343955726.us-central1.run.app](https://www.zero.xyz/host/arxiv-digest-72343955726.us-central1.run.app/llms.txt)