Runwall
Description
The active firewall and execution governance gateway for AI agents. Run Cursor, Claude Code, Cline, and custom agents safely on your infrastructure with OPA/Rego policies, real-time risk scoring, taint tracking, and Slack approval workflows.
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
Runwall
The Zero-Trust Execution Governance Platform for AI Agents
An intelligent security gateway that sits between AI reasoning models and real-world tools, databases, and environments.
Table of Contents
- Why Runwall?
- High-Level Architecture
- Core Features
- Key Workflows (Diagrams)
- Quick Start
- Client Integration
- Custom Agent Integration (Python)
- REST API & Dashboard
- License & Support
Why Runwall?
Everyone is wiring AI agents into production systems — Jira, Salesforce, internal databases, cloud providers, shell terminals — usually via protocols like the **Model Context Protocol (MCP)**. Unprotected, these connections behave like unlocked servers:
| Risk | Description |
|---|---|
| Infinite Loop Risk | A minor agent logic bug can trigger thousands of API calls in minutes, burning your budget. |
| Prompt Injection Threat | A malicious instruction hidden in a webpage or document can hijack your agent into destructive actions (e.g. "delete all users"). |
| The Trust Gap | Binary tool permissions can't express nuance — "read one record" |
Related Skills
Docker
---
Kubernetes
---
AWS Skills
AWS development with CDK best practices, cost optimization MCP servers, and serverless/event-driven architectu
Composio Split
Manage Split feature flags and experiments
**claude-code-router**
(25.3k ⭐) - Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interac
CLAUDE.md CI/CD Wiki
Community patterns for CLAUDE.md configuration in CI/CD pipelines.
