# LeakGuard by AgentGate

> LeakGuard by AgentGate is a paid API for AI agents from api.youraitools.co, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-23).

Scans text for leaked secrets, crypto keys, API credentials, and PII before it is sent to an LLM, tool, or webhook, returning a verdict, findings, and a redacted version of the text.

## Facts

- Endpoint: GET https://api.youraitools.co/leakguard/v1/lite?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/leakguard-by-agentgate-9c299801
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JBdai3cTHDxJqT_mIM6Ks

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 leakguard-by-agentgate-9c299801
```

Example prompt: Before you forward this message to the webhook, scan it with LeakGuard to check for any leaked secrets, API keys, or crypto seed phrases — give me the verdict, findings, and a redacted version: 'restored wallet from seed abandon ability able about above absent absorb abstract absurd abuse access; my aws key is AKIAIOSFODNN7EXAMPLE; contact me at user@example.com'

## When to prefer this

Use LeakGuard when an AI agent needs to intercept and sanitize text — prompts, tool arguments, logs, or webhook payloads — before transmission to prevent accidental exposure of crypto seed phrases, private keys, API credentials, or PII. It is especially valuable in agentic pipelines where user-supplied or LLM-generated text is forwarded to external services. Prefer this over generic regex-based checks because it performs BIP39 checksum validation, supports a wide catalog of named secret types, returns structured remediation advice, and provides a redacted output ready for safe forwarding.

## Known failure modes

- Missing required 'text' query parameter returns a validation error
- Text too long for the lite tier may be rejected or truncated
- Invalid 'style' or 'min_severity' enum values cause bad request errors
- Payment not provided or invalid x402 credentials returns 402 Payment Required
- Network timeout if the service is temporarily unavailable
- False negatives: novel or obfuscated secrets may not be detected
- False positives: benign text resembling key patterns may be flagged

## How this service works

Secret and PII detection API (redact before sending to an LLM). Find and redact leaked secrets before an AI agent sends text to an LLM, tool or webhook: crypto seed phrases (BIP39 checksum), EVM/Solana private keys, WIF, xprv, API keys (GitHub, AWS, Stripe, OpenAI, Anthropic, Slack...), JWT, PEM, cards, IBAN, SSN, email, phone. Verdict, findings and redacted text.

## Output

A JSON object containing: a top-level verdict string (e.g. WALLET_KEY_EXPOSED), a safe_to_send boolean, a max_severity level, a confidence rating, an array of findings (each with type, category, severity, confidence score, character offsets, preview, and remediation advice), a redacted version of the input text with secrets replaced, counts per finding type, and a checked_at timestamp.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "description": "Text to check before it is sent (prompt, tool arguments, log, message, file content). POST /v1/scan also accepts {\"json\": <any JSON payload>}."
      },
      "style": {
       "enum": [
        "label",
        "mask"
       ],
       "type": "string",
       "description": "label: [REDACTED:type] (default); mask: keep the last 4 digits / email domain for PII"
      },
      "types": {
       "type": "string",
       "description": "Optional comma-separated finding types or categories to report (wallet_key, secret, pii, email, ...)"
      },
      "min_severity": {
       "enum": [
        "low",
        "medium",
        "high",
        "critical"
       ],
       "type": "string"
      }
     },
     "description": "Search intents: secret detection api, pii redaction, api key leak scanner, seed phrase detection, data loss prevention api, redact text for llm"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "tier": {
       "type": "string"
      },
      "input": {
       "type": "object"
      },
      "counts": {
       "type": "object"
      },
      "engine": {
       "type": "string"
      },
      "verdict": {
       "type": "string"
      },
      "findings": {
       "type": "array"
      },
      "redacted": {
       "type": "string"
      },
      "checked_at": {
       "type": "string"
      },
      "confidence": {
       "type": "string"
      },
      "max_severity": {
       "type": "string"
      },
      "safe_to_send": {
       "type": "boolean"
      },
      "sources_failed": {
       "type": "array"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "tier": "lite",
  "input": {
   "kind": "text",
   "bytes": 185
  },
  "counts": {
   "email": 1,
   "bip39_mnemonic": 1,
   "aws_access_key_id": 1
  },
  "engine": "leakguard-0.1.0 (leakguard-engine/0.1.0)",
  "verdict": "WALLET_KEY_EXPOSED",
  "findings": [
   {
    "end": 130,
    "type": "bip39_mnemonic",
    "start": 37,
    "preview": "[REDACTED:bip39_mnemonic]",
    "category": "wallet_key",
    "severity": "critical",
    "validator": "bip39 checksum ok (12 words)",
    "confidence": 0.99,
    "remediation": "Treat the wallet as compromised: create a new seed offline and move all funds now. Never paste a seed phrase into a chat, prompt or tool."
   },
   {
    "end": 160,
    "type": "aws_access_key_id",
    "start": 140,
    "preview": "[REDACTED:aws_access_key_id]",
    "category": "secret",
    "severity": "high",
    "confidence": 0.9,
    "remediation": "Deactivate and rotate the access key in AWS IAM; check CloudTrail for use."
   },
   {
    "end": 185,
    "type": "email",
    "start": 170,
    "preview": "o***@example.com",
    "category": "pii",
    "severity": "medium",
    "confidence": 0.9,
    "remediation": "Personal data: send only if the recipient needs it (data minimization)."
   }
  ],
  "redacted": "agent log: restored wallet from seed [REDACTED:bip39_mnemonic]; aws key [REDACTED:aws_access_key_id]; contact [REDACTED:email]",
  "checked_at": "2026-10-22T19:07:15.225Z",
  "confidence": "high",
  "max_severity": "critical",
  "safe_to_send": false,
  "sources_failed": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/leakguard-by-agentgate-9c299801/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.youraitools.co](https://www.zero.xyz/host/api.youraitools.co/llms.txt)