ワンクリックでManusで任意のスキルを実行

audn-login

スター6

フォーク1

更新日2026年4月13日 16:51

Authenticate with Audn.ai for red-team security testing. Sets up OAuth login or API token. Run this before using any other audn skill. Use when the user needs to log in, authenticate, connect to Audn, or set up their API credentials.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

audn-ai

audn-ai/skills

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Audn.ai Authentication Setup

Set up authentication to the Audn.ai API. This must be done before using any other audn skill.

Step 1 — Check if MCP server is already configured

Run this command to check:

claude mcp get audn-redteam 2>/dev/null && echo "EXISTS" || echo "NOT_FOUND"

Step 2 — Register the MCP server (if NOT_FOUND)

If the MCP server is not configured, register it now. Run this exact command:

claude mcp add --transport http audn-redteam https://mcp.audn.ai/mcp/audn-rn8sx

This adds the Audn.ai MCP server with OAuth 2.1 support. Claude Code will auto-discover the OAuth endpoints at https://mcp.audn.ai/.well-known/oauth-authorization-server/mcp/audn-rn8sx and handle Dynamic Client Registration automatically.

Step 3 — IMPORTANT: Restart Claude Code

After adding the MCP server, the user MUST restart Claude Code for it to pick up the new server. MCP servers are only loaded at startup — they cannot be hot-reloaded mid-session.

Tell the user exactly this:

The MCP server has been registered. You need to restart Claude Code to activate it.

Exit this session — type /exit or press Ctrl+C

Start Claude Code again: claude

Run /audn-login again to continue authentication

STOP HERE. Do not proceed to Step 4 until the user has restarted and re-invoked this skill.

Step 4 — Authenticate via OAuth

After restarting, the MCP server should now appear in the server list. Tell the user:

Run /mcp now, select audn-redteam, and click "Authenticate". A browser window will open — log in at auth.audn.ai (or sign up at https://audn.ai if you don't have an account). After approving, your tokens are stored securely in the system keychain and refresh automatically.

Wait for the user to complete authentication.

Step 5 — Verify

After the user authenticates, check the MCP server status:

claude mcp get audn-redteam

If it shows connected, authentication is complete. All 34 Audn API tools are now available as MCP tools.

If the user has trouble with OAuth, fall back to API token method (see below).

Fallback — API Token Method

If OAuth doesn't work (firewall, SSH, container), use an API token instead:

Tell the user to generate a token at: https://audn.ai/dashboard/settings (API Keys section)
Then run in this session:

export AUDN_API_TOKEN="<their-token>"

For persistence, add to shell profile:

echo 'export AUDN_API_TOKEN="<token>"' >> ~/.zshrc

Verify it works:

curl -s -H "Authorization: Bearer $AUDN_API_TOKEN" https://audn.ai/api/user/profile

Should return user profile with success: true.

Output

After successful authentication (either method), report:

## Authenticated with Audn.ai

**Method**: MCP OAuth / API Token
**Status**: Connected

Ready to use audn skills:
- /audn-red <api-url> — Full red-team audit
- /audn-quick-scan <api-url> — Quick vulnerability scan
- /audn-agent-setup — Register an agent
- /audn-vuln-monitor — Check vulnerabilities

$ARGUMENTS

このリポジトリの他の Skills

同じリポジトリ

audn-agent-setup

audn-ai/skills

Register and verify an AI agent on Audn.ai for security testing. Supports text API agents (OpenAI, Anthropic, custom LLMs) and voice agents (Twilio, Genesys, Amazon Connect). Use when the user wants to add a new agent to test.

2026-04-136

audn-compliance-report

audn-ai/skills

Generate ISO 42001, SOC2, vulnerability, executive, or compliance reports from Audn.ai campaign results. Use when the user needs compliance evidence, audit documentation, or executive summaries of security testing.

2026-04-136

audn-quick-scan

audn-ai/skills

Quick vulnerability scan of an AI agent endpoint. Runs only critical and high-severity attack scenarios for a fast security check. Use for a rapid smoke test before a full red-team audit.

2026-04-136

audn-red

audn-ai/skills

Run a full adversarial red-team security audit against any AI agent (text or voice). Registers the agent, selects attack scenarios, executes a campaign, monitors progress, retrieves results, and generates a vulnerability report. Use when the user wants to security-test, red-team, pen-test, or audit an LLM or voice agent.

2026-04-136

audn-scenario-builder

audn-ai/skills

Create custom adversarial attack scenarios for AI agent red-teaming. Supports prompt injection, jailbreak, data extraction, social engineering, emotional manipulation, and role confusion attacks. Use when the user wants to design a specific attack test.

2026-04-136

audn-vuln-monitor

audn-ai/skills

List, triage, and monitor vulnerabilities detected across your AI agents. Shows severity ratings, categories, status, and remediation recommendations. Use when checking security posture or reviewing findings.

2026-04-136

name	audn-login
description	Authenticate with Audn.ai for red-team security testing. Sets up OAuth login or API token. Run this before using any other audn skill. Use when the user needs to log in, authenticate, connect to Audn, or set up their API credentials.
allowed-tools	Bash(claude mcp ) Bash(curl ) Bash(test ) Bash(echo ) Bash(export *)

Audn.ai Authentication Setup

Set up authentication to the Audn.ai API. This must be done before using any other audn skill.

Step 1 — Check if MCP server is already configured

Run this command to check:

claude mcp get audn-redteam 2>/dev/null && echo "EXISTS" || echo "NOT_FOUND"

Step 2 — Register the MCP server (if NOT_FOUND)

If the MCP server is not configured, register it now. Run this exact command:

claude mcp add --transport http audn-redteam https://mcp.audn.ai/mcp/audn-rn8sx

Step 3 — IMPORTANT: Restart Claude Code

After adding the MCP server, the user MUST restart Claude Code for it to pick up the new server. MCP servers are only loaded at startup — they cannot be hot-reloaded mid-session.

Tell the user exactly this:

The MCP server has been registered. You need to restart Claude Code to activate it.

Exit this session — type /exit or press Ctrl+C

Start Claude Code again: claude

Run /audn-login again to continue authentication

STOP HERE. Do not proceed to Step 4 until the user has restarted and re-invoked this skill.

Step 4 — Authenticate via OAuth

After restarting, the MCP server should now appear in the server list. Tell the user:

Run /mcp now, select audn-redteam, and click "Authenticate". A browser window will open — log in at auth.audn.ai (or sign up at https://audn.ai if you don't have an account). After approving, your tokens are stored securely in the system keychain and refresh automatically.

Wait for the user to complete authentication.

Step 5 — Verify

After the user authenticates, check the MCP server status:

claude mcp get audn-redteam

If it shows connected, authentication is complete. All 34 Audn API tools are now available as MCP tools.

If the user has trouble with OAuth, fall back to API token method (see below).

Fallback — API Token Method

If OAuth doesn't work (firewall, SSH, container), use an API token instead:

Tell the user to generate a token at: https://audn.ai/dashboard/settings (API Keys section)
Then run in this session:

export AUDN_API_TOKEN="<their-token>"

For persistence, add to shell profile:

echo 'export AUDN_API_TOKEN="<token>"' >> ~/.zshrc

Verify it works:

curl -s -H "Authorization: Bearer $AUDN_API_TOKEN" https://audn.ai/api/user/profile

Should return user profile with success: true.

Output

After successful authentication (either method), report:

## Authenticated with Audn.ai

**Method**: MCP OAuth / API Token
**Status**: Connected

Ready to use audn skills:
- /audn-red <api-url> — Full red-team audit
- /audn-quick-scan <api-url> — Quick vulnerability scan
- /audn-agent-setup — Register an agent
- /audn-vuln-monitor — Check vulnerabilities

$ARGUMENTS