Skip to content

[docs-diagram] Add Safe Outputs permission-isolation diagram #56828

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pelikhan merged 1 commit into from
Aug 29, 2026
Merged

[docs-diagram] Add Safe Outputs permission-isolation diagram #56828

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 72 additions & 0 deletions docs/src/assets/diagrams/architecture-2026-08-29.svg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
4 changes: 4 additions & 0 deletions docs/src/content/docs/introduction/architecture.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ head:
---

import { Aside } from '@astrojs/starlight/components';
import { Image } from 'astro:assets';
import safeOutputsIsolation from '../../../assets/diagrams/architecture-2026-08-29.svg';

GitHub Agentic Workflows (gh-aw) runs AI coding agents — GitHub Copilot, Claude Code, OpenAI Codex, or Google Gemini — inside GitHub Actions with a defense-in-depth security architecture that protects against prompt injection, rogue MCP servers, and compromised agents. This document provides an overview of the security model and its key components.

Expand Down Expand Up @@ -165,6 +167,8 @@ flowchart LR
LABEL --> API
```

<Image src={safeOutputsIsolation} alt="Diagram showing the agent job writing an agent_output.json artifact, which a threat detection job analyzes for secret leaks and malicious patches; only when approved do scoped safe-output jobs such as create_issue, add_comment, and create_pull_request call the GitHub API, while the agent itself never holds write permissions" />

<Aside type="tip">
The SafeOutputs subsystem provides security by design: the agent never requires write permissions because all write operations are performed by separate, validated jobs with minimal scoped permissions.
</Aside>
Expand Down
Loading