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

> AgentProbe v1.0.0 – Bilingual LLM-Agent Adversarial Test Pack Grader 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).

Scores an LLM agent against 53 hand-authored, OWASP-mapped adversarial test cases in English and Chinese, returning a graded result JSON.

## Facts

- Endpoint: POST https://agentprobe.pythonanywhere.com/v1/grade
- 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-grader-260a103c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_cQZ6xue7gO93jXz_i9U-L

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-grader-260a103c -d '<json body>'
```

Example prompt: Run the Chinese adversarial test pack from AgentProbe against my agent and tell me how many cases it passed — I want to see the OWASP-mapped grade results.

## When to prefer this

Choose this endpoint when you need to evaluate an OpenAI-compatible LLM agent against a curated, OWASP-mapped adversarial test suite in English and/or Chinese without writing your own test harness. It is especially useful for red-teaming, safety auditing, or CI/CD gating of agents where bilingual (EN+ZH) adversarial coverage matters and you want structured, reproducible scores per call.

## Known failure modes

- Invalid or unrecognized pack name returns an error or empty result
- Malformed POST body causes a 400 or parsing error
- Agent endpoint being tested is unreachable, causing timeout or connection failure
- Payment not processed correctly via x402, resulting in 402 Payment Required
- Rate limiting or server overload on pythonanywhere hosting returns 5xx

## 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

A JSON object containing the test pack name (e.g. 'zh-agent-adversarial') and the count of adversarial cases evaluated, along with grading results indicating how the agent performed against each OWASP-mapped adversarial scenario.

## 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-grader-260a103c/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)