# AgentProbe v1.0.0 – Bilingual LLM-Agent Adversarial Test Pack

> AgentProbe v1.0.0 – Bilingual LLM-Agent Adversarial Test Pack is a paid API for AI agents from agentprobe.pythonanywhere.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-14).

Returns a pack of 53 hand-authored, OWASP-mapped adversarial test cases in English and Chinese for evaluating the security robustness of OpenAI-compatible LLM agents.

## Facts

- Endpoint: GET https://agentprobe.pythonanywhere.com/v1/pack
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentprobe-v1-0-0-bilingual-llm-agent-adversarial-test-pack-9f1f4afb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qELDYN5S_IoiN4_oHvbFE

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 agentprobe-v1-0-0-bilingual-llm-agent-adversarial-test-pack-9f1f4afb
```

Example prompt: Fetch me the AgentProbe adversarial test pack — I need all 53 OWASP-mapped cases in both English and Chinese so I can start red-teaming my OpenAI-compatible agent.

## When to prefer this

Choose this endpoint when you need a ready-made, OWASP-aligned adversarial test suite specifically designed for LLM agents and need bilingual (English + Chinese) coverage out of the box. It is preferable to hand-rolling test cases when you want structured, security-framework-mapped prompts with a bundled scoring harness that works with any OpenAI-compatible model, and when you need results quickly without writing test infrastructure from scratch.

## Known failure modes

- Payment not fulfilled (x402 payment required) — endpoint returns 402 before delivering the pack
- Network timeout on PythonAnywhere free-tier hosting — service may be slow or unavailable during cold starts
- Invalid or missing pack identifier — may return empty or malformed JSON
- Rate limiting if too many requests are made in quick succession

## How this service works

53 hand-authored, OWASP-mapped adversarial cases (EN+ZH) plus a zero-dependency MIT harness that scores any OpenAI-compatible LLM agent. US$6.99.

## Output

Returns a JSON object containing the pack identifier (e.g. 'zh-agent-adversarial') and the count of adversarial test cases included (e.g. 53), along with the full set of hand-authored, OWASP-mapped prompts in both English and Chinese that can be run against any OpenAI-compatible LLM agent using the bundled zero-dependency MIT harness.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "pack": "zh-agent-adversarial",
  "count": 2
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentprobe-v1-0-0-bilingual-llm-agent-adversarial-test-pack-9f1f4afb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentprobe.pythonanywhere.com](https://www.zero.xyz/host/agentprobe.pythonanywhere.com/llms.txt)