# CVE Brief Digest – LLM Security Advisory Summary

> CVE Brief Digest – LLM Security Advisory Summary is a paid API for AI agents from oracles-production.up.railway.app, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-15).

Returns an LLM-generated natural-language digest summarizing the most severe new CVEs discovered within a specified time window.

## Facts

- Endpoint: GET https://oracles-production.up.railway.app/v1/cve/brief
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cve-brief-digest-llm-security-advisory-summary-a8267a4e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_27QcNvUzUcGtPpDqINXEu

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 cve-brief-digest-llm-security-advisory-summary-a8267a4e
```

Example prompt: Give me an LLM-written digest of the most severe CVEs disclosed since January 1, 2025 — I want to understand which new vulnerabilities are most critical right now.

## When to prefer this

Choose this endpoint when you need a concise, human-readable narrative summary of recent high-severity CVEs rather than raw CVE data. Ideal for security briefings, executive summaries, or automated threat digests where an LLM-written plain-English overview is more useful than structured CVE records. Prefer this over GHSA advisory endpoints when the focus is on CVEs specifically rather than GitHub-tracked advisories.

## Known failure modes

- If no CVEs are found in the specified window, brief may be empty or minimal
- Invalid date-time format for 'since' parameter returns a 400 error
- Service unavailability on Railway hosting may cause 503 responses
- LLM generation failure may fall back to template-based output (generatedBy: 'template')
- Very large windows may increase latency or cost

## How this service works

An LLM-written digest of the most severe new CVEs in the window.

## Output

Returns a JSON object containing: a 'brief' field with a human-readable, LLM-written narrative summarizing the most severe recent CVEs; a 'generatedBy' field indicating whether it was produced by an LLM or a template; and a 'basedOnChanges' integer showing how many CVE records were analyzed to produce the digest.

## 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",
     "properties": {
      "since": {
       "type": "string",
       "format": "date-time",
       "description": "Window start (default: last 30 days)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "brief": {
       "type": "string"
      },
      "generatedBy": {
       "enum": [
        "llm",
        "template"
       ],
       "type": "string"
      },
      "basedOnChanges": {
       "type": "integer"
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cve-brief-digest-llm-security-advisory-summary-a8267a4e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from oracles-production.up.railway.app](https://www.zero.xyz/host/oracles-production.up.railway.app/llms.txt)
