From abbc3a9578f527067e46d2cca1170774c9644a8c Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Wed, 9 Sep 2026 09:07:53 +0000 Subject: [PATCH] Add inline gh-aw doc links to workshop files (batch 101-110) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- workshop/05b-agentic-workflows-security.md | 2 +- workshop/06-install-gh-aw.md | 2 +- workshop/09-agentic-editing.md | 2 +- workshop/14b-pr-reviewer-workflow.md | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/workshop/05b-agentic-workflows-security.md b/workshop/05b-agentic-workflows-security.md index 2d96d9f3..581afb8b 100644 --- a/workshop/05b-agentic-workflows-security.md +++ b/workshop/05b-agentic-workflows-security.md @@ -17,7 +17,7 @@ Letting an AI agent act on your repository on a [schedule](https://github.github ## Safe by design: sandbox + guardrailed outputs - **A [sandbox](https://github.github.com/gh-aw/reference/sandbox/) around the agent.** The agent runs isolated inside the [Agent Workflow Firewall](https://github.github.com/gh-aw/reference/sandbox/), with **read-only** access to your repo and [network egress](https://github.github.com/gh-aw/reference/network/) limited to the domains you allow. Even if a [prompt injection](https://github.github.com/gh-aw/reference/threat-detection/) or a compromised tool tries to reach out or exfiltrate data, the firewall blocks anything outside the allowlist. -- **A guardrailed [safe-output](https://github.github.com/gh-aw/reference/safe-outputs/) system for writes.** The agent never holds write permissions. Instead, it emits a *structured request* — "create this issue," "post this comment" — and a separate, permission-scoped job validates and executes it, applying per-operation limits (max counts, label and title constraints, allowed repos). That separation gives you least privilege, defense against prompt injection, and a full audit trail of every action. +- **A guardrailed [safe-output](https://github.github.com/gh-aw/reference/safe-outputs/) system for writes.** The agent never holds write [permissions](https://github.github.com/gh-aw/reference/permissions/). Instead, it emits a *structured request* — "create this issue," "post this comment" — and a separate, permission-scoped job validates and executes it, applying per-operation limits (max counts, label and title constraints, allowed repos). That separation gives you least privilege, defense against prompt injection, and a full audit trail of every action. The security jobs in the run log above map to these boundaries: **activation** checks the agent is authorized to run, the **agent** runs sandboxed behind the firewall, **detection** scans for malicious behavior, and **safe-outputs** applies changes within the guardrails. diff --git a/workshop/06-install-gh-aw.md b/workshop/06-install-gh-aw.md index 84d37927..ef7604c8 100644 --- a/workshop/06-install-gh-aw.md +++ b/workshop/06-install-gh-aw.md @@ -54,7 +54,7 @@ Need more help? See [Side Quest: Install gh-aw Troubleshooting](side-quest-06-01 gh aw doctor ``` -This verifies your GitHub CLI authentication using the same setup checks `gh-aw` expects before later authoring and compile steps. +This verifies your GitHub CLI authentication using the same setup checks `gh-aw` expects before later authoring and [compile](https://github.github.com/gh-aw/reference/compilation-process/) steps. Expected result: a success message confirming GitHub CLI authentication. If it fails, use [Side Quest: Install gh-aw Troubleshooting](side-quest-06-01-install-troubleshooting.md), then rerun `gh aw doctor`. diff --git a/workshop/09-agentic-editing.md b/workshop/09-agentic-editing.md index 855b2b88..28e6c848 100644 --- a/workshop/09-agentic-editing.md +++ b/workshop/09-agentic-editing.md @@ -135,7 +135,7 @@ The skill applies techniques such as removing redundant instructions, consolidat
:desktop_computer: Terminal path -Review the Markdown body of your workflow and remove any sentences that repeat the same constraint or restate something already enforced by frontmatter (for example, "post only one comment" if `safe-outputs` already limits you to one comment). Recompile after each removal so you can verify nothing breaks. +Review the Markdown body of your workflow and remove any sentences that repeat the same constraint or restate something already enforced by [frontmatter](https://github.github.com/gh-aw/reference/frontmatter/) (for example, "post only one comment" if `safe-outputs` already limits you to one comment). Recompile after each removal so you can verify nothing breaks.
diff --git a/workshop/14b-pr-reviewer-workflow.md b/workshop/14b-pr-reviewer-workflow.md index ac337478..ef1d7f6e 100644 --- a/workshop/14b-pr-reviewer-workflow.md +++ b/workshop/14b-pr-reviewer-workflow.md @@ -82,7 +82,7 @@ safe-outputs: --- ``` -Notice that the agent job has no repository or pull request write permission. `copilot-requests: write` only authenticates Copilot. The `submit-pull-request-review` [safe output](https://github.github.com/gh-aw/reference/safe-outputs/) performs the controlled repository write after the agent finishes. `APPROVE` is intentionally absent because the default GitHub Actions token cannot approve pull requests. +Notice that the agent job has no repository or pull request write permission. `copilot-requests: write` only authenticates Copilot. The `submit-pull-request-review` [safe output](https://github.github.com/gh-aw/reference/safe-outputs/) performs the controlled repository write after the agent finishes. `APPROVE` is intentionally absent because the default [GitHub Actions](https://github.github.com/gh-aw/reference/glossary/#github-actions) token cannot approve pull requests. Near the bottom, look for the two reusable blocks: