メニュー
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.
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。
SOC 職業分類に基づく
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.
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.
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.
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.
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.
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.
| name | audn-compliance-report |
| description | 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. |
Generate compliance and security reports from completed campaign data.
Bearer token via AUDN_API_TOKEN env var. Base URL: https://audn.ai.
All requests include header: Authorization: Bearer $AUDN_API_TOKEN.
If user provides a campaign ID, use it directly.
If not, list recent campaigns:
GET /api/campaigns?limit=10&status=completed
Present the list and let the user choose, or auto-select the most recent completed campaign.
Available report types:
| Type | Use Case |
|---|---|
iso_42001 | ISO/IEC 42001 AI management system compliance evidence |
soc2 | SOC 2 Type II security control evidence |
vulnerability | Technical vulnerability assessment with CVSS-style ratings |
executive | Board-level summary with risk posture and trends |
compliance | General compliance overview combining multiple frameworks |
Parse user intent to select the right type. Default to vulnerability if unclear.
If user says "all" or "full", generate vulnerability + executive + compliance.
POST /api/reports
Content-Type: application/json
{
"type": "<report_type>",
"campaign_id": "<campaign_id>",
"name": "<Report Type> Report — <Campaign Name> — <date>"
}
Save returned report_id.
GET /api/reports/<report_id>
Poll every 5 seconds until status is completed or failed.
When complete, the response includes:
file_url — downloadable report URLmetadata — report contents/summary## Report Generated
**Type**: ISO 42001 / SOC2 / Vulnerability / Executive / Compliance
**Campaign**: <campaign name>
**Status**: Completed
**Generated**: <timestamp>
**Download**: <file_url>
### Summary
<Extract key findings from metadata if available>
- Total tests: X
- Vulnerabilities: Y (critical: A, high: B, medium: C, low: D)
- Compliance status: passing/failing
- Risk level: low/medium/high/critical
If generating multiple reports, present each in sequence.
$ARGUMENTS