360 Secure SkillHub
360 安全技能中心

MetatextAI

核心功能包括创建/列出AI护栏策略、评估聊天记录合规性、运行红队测试扫描。典型场景为管理AI安全护栏、检测对话合规性、开展安全测试。通过oo CLI执行命令，输入需匹配对应操作的JSON schema，输出含执行结果及ID的JSON响应。支持首次安装CLI、登录、连接账号等初始化操作，写操作需获用户确认。

oomol
oomol
热度 54.11
最近更新 2026-09-20 11:38:23
分类：自动化依赖：代码执行 / MCP 服务应用场景：API 集成 / 自动化脚本

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add oo-metatextai
Metadata
name
oo-metatextai
description
MetatextAI (metatext.ai). Use this skill for ANY MetatextAI request — reading, creating, and updating data. Whenever a task involves MetatextAI, use this skill instead of calling the API directly.
allowed-tools
["Bash(oo *)"]
metadata
{"title":"MetatextAI","author":"OOMOL","version":"1.0.5","services":["metatextai"],"icon":"https://static.oomol.com/logo/third-party/metatextai.svg"}

MetatextAI

Operate MetatextAI through your OOMOL-connected account. This skill calls the metatextai connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Running an action

Assume the user has already installed the oo CLI, signed in, and connected MetatextAI. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "metatextai" --action "<action_name>"

2. Run the action with a JSON payload that matches the input schema:

oo connector run "metatextai" --action "<action_name>" --data '<json>' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action is listed below with a one-line description; actions that change state carry a [write] or [destructive] tag. Before constructing --data, fetch the action's live schema with oo connector schema to get its authoritative input fields.

Available actions

  • create_policy — Create one guardrail policy for the connected MetatextAI application. [write]
  • evaluate — Evaluate one chat transcript against the connected MetatextAI application's configured guardrails.
  • list_policies — List all guardrail policies configured for the connected MetatextAI application.
  • run_test_scan — Run a MetatextAI red-team test scan for the connected application with the selected probes. [write]

Safety

  • Untagged actions are reads (get / list / search) — safe to run directly.
  • Actions tagged [write] change MetatextAI state — confirm the exact payload and effect with the user before running.
  • Actions tagged [destructive] remove or overwrite data — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux

    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell

  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login

  • scope_missing / credential_expired / app_not_ready / app_not_found — MetatextAI is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:

    https://console.oomol.com/app-connections?provider=metatextai

  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources