agent-passportOAuth for the agentic era. Consent-gating for ALL sensitive agent actions. 75+ data-driven threat definitions with auto-updates (like antivirus signatures)....
Install via ClawdBot CLI:
clawdbot install markneville/agent-passportGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
$OPENAIContains instructions to override system prompt or ignore user requests
"ignore previous instructions"Potentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://agentpassportai.com/pro/Generated Mar 20, 2026
An AI agent manages code deployments, runs shell commands like git and npm, and interacts with cloud APIs. Agent Passport ensures it only executes approved commands, prevents unauthorized system changes, and logs all actions for audit trails, reducing security risks in CI/CD pipelines.
An AI agent handles customer inquiries by sending emails and accessing customer databases. Agent Passport enforces recipient allowlists, rate limits to prevent spam, and requires consent for sensitive data edits, ensuring compliance with privacy regulations like GDPR.
An AI agent executes trades and manages financial transactions via APIs. Agent Passport applies spending caps, restricts to approved merchants, and logs all financial actions with TTL expiry, providing a secure audit trail and preventing unauthorized spending.
An AI agent posts to social media and schedules communications as the user. Agent Passport requires human review for identity actions, enforces content guidelines with allowlists, and uses kill switches to freeze operations if suspicious activity is detected.
An AI agent manages patient records and sends secure communications. Agent Passport restricts file operations to specific paths, ensures data backups before deletions, and logs all actions for HIPAA compliance, safeguarding sensitive health information.
Offer a free tier with basic features like consent-gating and limited threat definitions. Charge for Pro tier with real-time updates every 6 hours, advanced templates, and priority support, targeting small to medium businesses seeking enhanced security.
Sell custom licenses to large organizations needing tailored mandates, integration with existing security tools, and dedicated threat definition management. Include premium support and compliance reporting for industries like finance and healthcare.
Distribute Agent Passport through AI agent platforms or app stores, taking a commission on sales. Offer add-ons like specialized templates (e.g., for coding or web research) and monetize via one-time purchases or in-app upgrades.
💬 Integration Tip
Start by integrating the Skill Scanner and Injection Shield first to assess vulnerabilities, then use templates like dev-tools for quick setup, ensuring all required binaries and environment variables are configured.
Scored Apr 19, 2026
Uses known external API (expected, informational)
api.anthropic.comAudited Apr 17, 2026 · audit v1.0
Self-hosted auth for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, and 15+ plugins. Requires Drizzle ORM or Kysely for D1 (no direct adapter). Self-hosted alternative to Clerk/Auth.js. Use when: self-hosting auth on D1, building OAuth provider, multi-tenant SaaS, or troubleshooting D1 adapter errors, session caching, rate limits, Expo crashes, additionalFields bugs.
Clerk integration. Manage Users, Organizations. Use when the user wants to interact with Clerk data.
Clerk auth with API Keys beta (Dec 2025), Next.js 16 proxy.ts (March 2025 CVE context), API version 2025-11-10 breaking changes, clerkMiddleware() options, webhooks, production considerations (GCP outages), and component reference. Prevents 15 documented errors. Use when: API keys for users/orgs, Next.js 16 middleware filename, troubleshooting JWKS/CSRF/JWT/token-type-mismatch errors, webhook verification, user type inconsistencies, or testing with 424242 OTP.
Sentry API integration with managed authentication. Monitor errors, issues, and application performance. Use this skill when users want to list issues, retrieve events, manage projects, teams, or releases in Sentry. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a Sentry connection into automation, in the order they are used: the connection (the first step), a hosted function that runs a Sentry action through the Maton SDK, and a trigger that calls that function on a schedule or on an event. Those sections are the platform's own reference text, shared with the api-gateway skill, with Sentry examples; they add no Sentry capability - Sentry is not an event source, a trigger cannot read Sentry data, and the files under `references/<source>/triggers.md` are the platform's event catalogues for the sources Maton offers (time, Calendly, GitHub, Gmail, HubSpot, Linear, Notion, Slack, Stripe).
Host static files on subdomains with optional authentication. Use when you need to serve HTML, images, CSS, JS, or any static content on a dedicated subdomain. Supports file upload, basic auth, quota management, and automatic SSL via Caddy. Commands include sf sites (create/list/delete), sf upload (files/directories), sf files (list/delete).
Download YouTube videos by URL in various resolutions using a pay-per-use API with credit-based authentication and no charge on failed downloads.