# DestructGuard Command Score

> DestructGuard Command Score is a paid API for AI agents from hermesplant.com, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-15).

Scores an AI agent command or action for destructive risk, returning a risk level and recommended safety action such as blocking until human approval.

## Facts

- Endpoint: GET https://hermesplant.com/api/agent-services/destructguard/score
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/destructguard-command-score-abc1d23a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7wgSbT3J10Q3a6ThfgTqi

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 destructguard-command-score-abc1d23a
```

Example prompt: Run a DestructGuard risk score on this command before I let the agent execute it — the command is 'delete all inactive user accounts from the production database' — I need to know if it's critical risk and whether it requires human approval before proceeding.

## When to prefer this

Use DestructGuard Command Score when you need a fast, per-command safety gate in an AI operator or autonomous agent pipeline — especially before executing irreversible, high-impact, or production-affecting actions. Prefer this over generic policy checks when you need a structured risk classification with explicit approval flags and recommended actions compatible with x402 payment flows.

## Known failure modes

- Missing or malformed command payload returns a 400 error
- Payment not attached or insufficient USDC balance causes a 402 response
- Ambiguous or empty command text may result in an indeterminate risk score
- Rate limiting or quota exceeded may return a 429 error
- Service downtime returns a 503 with no score

## How this service works

Deterministic risk scorer for autonomous-agent commands. Scores a shell, SQL, or git action for destructive, deployment, and data-mutation risk before execution and returns a risk level, the matched policy rules, and an approve-or-block recommendation. Pure rules, evidence per match, no fabrication.

## Output

A JSON object containing a risk level (e.g. 'critical'), a status string ('scored'), the service name ('destructguard-command-score'), a unique request ID (dg_<uuid>), a boolean indicating whether approval is required, and a recommended action string (e.g. 'block_until_explicit_human_or_policy_approval').

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "cwd": {
   "type": "string"
  },
  "repo": {
   "type": "string"
  },
  "actor": {
   "type": "string"
  },
  "intent": {
   "type": "string"
  },
  "command": {
   "type": "string",
   "description": "Shell command or agent action to score"
  },
  "diffStat": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "risk": "critical",
  "status": "scored",
  "service": "destructguard-command-score",
  "requestId": "dg_<uuid>",
  "requiresApproval": true,
  "recommendedAction": "block_until_explicit_human_or_policy_approval"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/destructguard-command-score-abc1d23a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from hermesplant.com](https://www.zero.xyz/host/hermesplant.com/llms.txt)