# TensorFeed AI Stack CVE Intelligence Feed

> TensorFeed AI Stack CVE Intelligence Feed is a paid API for AI agents from tensorfeed.ai, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-13).

Returns filtered, ranked CVE security disclosures specifically covering AI inference, agent frameworks, training libraries, vector databases, model gateways, and MCP tool layers, sorted by exploited-in-wild and critical severity first.

## Facts

- Endpoint: GET https://tensorfeed.ai/api/premium/ai-cves/ai-stack-cves
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tensorfeed-ai-00d09525
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FmxSp8kPHwv05CMiHjTZt

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 tensorfeed-ai-00d09525
```

Example prompt: Pull the latest AI stack CVEs for me — I need the full list ranked by severity with exploited-in-wild ones at the top, tagged by AI category like inference, vector DB, agent frameworks, and model gateways.

## When to prefer this

Use this endpoint when you specifically need CVE intelligence scoped to the AI/ML software stack — inference engines, vector databases, agent frameworks, model gateways, and MCP tools — rather than generic CVE feeds. Prefer this over broad security advisory APIs when you want pre-filtered, AI-category-tagged, severity-ranked results with exploited-in-wild prioritization, saving the agent from having to filter and rank a massive undifferentiated CVE stream.

## Known failure modes

- Payment not fulfilled — 402 response if x402 payment header is missing or insufficient
- No new CVEs available — empty result set if no fresh disclosures in the filtered AI categories
- Rate limiting or upstream GitHub Security Advisory data lag — stale or delayed results
- Network timeout on upstream data aggregation

## How this service works

AI-stack CVE intelligence. Filters fresh security disclosures to vendors and products in the AI inference, agent framework, training, vector DB, model gateway, and MCP tool layers. Each paper carries a tf_ai_category tag and a severity_rank, sorted with exploited-in-wild and critical-severity first. 99.8% of underlying data is from GitHub Security Advisories (CC BY 4.0).

## Output

A ranked list of fresh CVE security disclosures filtered to AI-stack vendors and products (inference engines, agent frameworks, training libraries, vector DBs, model gateways, MCP tools), each entry tagged with tf_ai_category and severity_rank, sorted with exploited-in-wild and critical-severity entries first. Data is sourced 99.8% from GitHub Security Advisories.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "additionalProperties": false
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tensorfeed-ai-00d09525/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tensorfeed.ai](https://www.zero.xyz/host/tensorfeed.ai/llms.txt)