Use the AWF (Agentic Workflow Firewall) to run commands with network isolation and domain whitelisting. Provides L7 HTTP/HTTPS egress control for AI agents.
github/gh-aw-firewall
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 9
- GitHub stars
- 149
- GitHub forks
- 77
Loading the repository README…
Skills in this repository
Showing 9 of 9 collected skills.
Practical Python scripts for debugging awf - parse logs, diagnose issues, inspect containers, test domains
Debug the AWF firewall by inspecting Docker containers (awf-squid, awf-agent), analyzing Squid access logs, checking iptables rules, and troubleshooting blocked domains or network issues.
Diagnose an AWF (Agentic Workflow Firewall) failure from an error, workflow run URL, or symptom. Covers auth (api-proxy, enterprise/BYOK Copilot, OIDC, mcpg), ARC/DinD and self-hosted runners, alternative runtimes (gVisor/Kata/chroot), Squid/DNS/egress…
Debug GitHub Actions workflows by downloading logs, analyzing summaries, and understanding how agentic workflows and the AWF firewall work together.
Decide and implement how to support a new LLM provider or agent engine in AWF - either as a proxied provider (api-proxy adapter) or a direct-API engine (domain allowlist only), e.g. Cursor, Aider, or any tool that calls its own endpoint.
Prepare an open pull request for merge from a GitHub Copilot cloud agent. Drives Reviews, local validation, and Mergeable to a ready state. Does not merge, and cannot trigger CI.
Regenerate and post-process all agentic workflows. Use when gh-aw is updated, workflow .md files change, or when asked to recompile/regenerate workflows.
Use the AWF (Agentic Workflow Firewall) to run commands with network isolation and domain whitelisting. Provides L7 HTTP/HTTPS egress control for AI agents.
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/github/gh-aw-firewall.