# StealthGuard Prompt Firewall

> StealthGuard Prompt Firewall is a paid API for AI agents from stealthguard-402.onrender.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-19).

Scrubs incoming HTTP request bodies for prompt-injection attacks and wallet-drainer patterns before they reach an AI agent's context window.

## Facts

- Endpoint: POST https://stealthguard-402.onrender.com/v1/security/prompt-firewall?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/stealthguard-prompt-firewall-d3fab1aa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_NgkLviV6JYCaE0nrlG5dm

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 stealthguard-prompt-firewall-d3fab1aa -d '<json body>'
```

Example prompt: Before you process that third-party API response, run it through the prompt firewall to check for any prompt-injection or wallet-drainer content hiding in the JSON body.

## When to prefer this

Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — third-party APIs, user submissions, webhooks, or scraped data — and you need a fast, cheap ($0.001 USDC), deterministic pre-filter before that content enters an LLM context window. Prefer it over general-purpose LLM-based safety checks when you need ultra-low latency and deterministic results rather than probabilistic judgments.

## Known failure modes

- Malformed or missing 'input' object returns a 400-level validation error
- Non-JSON bodyType values are rejected as the enum only supports 'json'
- Ambiguous or obfuscated injections may evade deterministic pattern matching
- Service unavailability on Render cold-start may cause latency spikes or timeouts
- Overly aggressive pattern matching may produce false positives on benign payloads

## How this service works

Ultra-fast deterministic prompt-injection and wallet-drainer scrubber for agent context windows.

## Output

Returns a deterministic TRUST or BLOCK verdict indicating whether the submitted HTTP body contains prompt-injection patterns or wallet-drainer instructions, along with flagged content details so the agent can decide whether to proceed or discard the payload.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Raw text context to scrub for prompt injections"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/stealthguard-prompt-firewall-d3fab1aa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from stealthguard-402.onrender.com](https://www.zero.xyz/host/stealthguard-402.onrender.com/llms.txt)