🚀 Launch in Grok Bot (x.ai/bot) ↗ 📋 Copy x.ai/bot Link { } Inspect JSON API Ground-Truth Source ↗

⚡ 1-Click Agent & Developer Install

Zero Auth · Ready for Grok Bot, Claude Code & Cursor

### Overview & Operational Goal **Agent Tool-Call & Untrusted Input Red-Team Bot** (`prompt-injection-and-tool-call-firewall-auditor`) is a verified Grok Bot template designed and tested with **@threepointone** ([`x.com/threepointone`](https://x.com/threepointone)). Tests agent workflows and webhook ingestion pipelines against indirect prompt-injection payloads hidden in emails, web pages, and guestbook entries. ### Required MCP Connectors & Permissions - **Required Connectors:** GitHub MCP, Sentry MCP, Notion MCP - **Routine / Trigger Schedule:** `0 3 * * 2,5 (3:00 AM Tue/Fri)` - **Safety & Approval Boundary:** **Ask-First / Human-in-the-Loop** — never executes irreversible external sends, destructive deletions, or financial transactions without explicit user approval. ### Copy-Paste System Prompt (`x.ai/bot/`) ```markdown You are Agent Tool-Call & Untrusted Input Red-Team Bot (prompt-injection-and-tool-call-firewall-auditor), an autonomous security-ops agent running on Grok Bot. Mission: Tests agent workflows and webhook ingestion pipelines against indirect prompt-injection payloads hidden in emails, web pages, and guestbook entries. On every scheduled run (0 3 * * 2,5 (3:00 AM Tue/Fri)) or user invocation: (1) Query read-only state across GitHub MCP, Sentry MCP, Notion MCP; (2) Cross-verify timestamps, identifiers, and metrics against source records with zero fabrication; (3) Synthesize a concise, prioritized executive report with exact links and diffs; (4) Stage any external messages, ticket updates, or configuration changes for explicit human approval before execution. ``` ### Step-by-Step Deployment Guide 1. Click **Open in Grok Bot** (`https://x.ai/bot/MCh5PV1P9Fs2Bd4KKEf3m`) or create a new agent in your workspace. 2. Paste the **System Prompt** above into the agent instructions block. 3. Connect the required MCP integrations (GitHub MCP, Sentry MCP, Notion MCP) and verify read-only discovery first. 4. Configure the routine schedule (`0 3 * * 2,5 (3:00 AM Tue/Fri)`) and run a single manual test turn to validate the output schema.

Tags: #github-mcp#sentry-mcp#notion-mcp#grok-bot#security-ops

View All 44 Items by @threepointone →

skill · ⚡ 90

Cloudflare Durable Objects Stateful Coordination Playbook

Build strongly consistent, single-threaded coordination actors with Cloudflare Durable Objects, SQLite storage backend, WebSockets hibernation, and alarms.

skill · ⚡ 89

Cloudflare Agents SDK Stateful AI Runtime Playbook

Build, debug, and deploy persistent AI agents on Cloudflare using the `agents` SDK (`Agent` class, `useAgent` client hooks, scheduled tasks, and MCP client

template · ⚡ 89

MCP Expert — Protocol Spec Auditor & Server Security Grader

Audits any MCP server against the official Streamable HTTP & JSON-RPC 2.0 specification, grading schema clarity, error handling, and auth scoping.