Online Access Free GH-600 Exam Questions

While upgrading App1, the agent identifies 47 issues, including a security vulnerability, and 46 API incompatibilities across different projects.
Which two actions are unsafe to delegate to the agent and require human involvement? Each correct answer presents a complete solution.
NOTE: Each correct selection is worth one point.

• A.Validate the assessment.md file for accuracy.
• B.Review the plan.md file for dependencies.
• C.Approve all Git commits.
• D.Validate whether the tasks.md file exists.
• E.Generate the assessment.md file.

Your team wants Copilot's suggestions to reflect knowledge of internal library APIs that are not publicly documented and not present in the codebase being edited. What is the most appropriate solution?

• A.Add the internal docs as copilot-instructions.md
• B.Use .copilotignore to hide public APIs
• C.Enable plan mode
• D.Connect an MCP server that exposes the internal documentation

You have a GitHub repository that stores custom GitHub Copilot agents in the .github/agents/ folder.
You have an agent named lead-dev.agent.md that must invoke a specialist subagent named security-reviewer.
Evaluation results show that lead-dev attempts to invoke security-reviewer, but the subagent call fails to run.
You need to ensure that lead-dev can invoke security-reviewer.
How should you complete the YAML frontmatter of the agent profile? To answer, drag the appropriate values to the correct targets.

Correct Answer:

You have a GitHub Actions workflow that runs a multi-agent job. Each agent uploads its output as a workflow artifact.
A completed workflow run produces unexpected code changes, and the job logs do NOT show the agents' intermediate outputs.
You need to retrieve the agents' captured outputs from the completed run for post-hoc analysis.
What should you do in GitHub Actions?

• A.Rerun the workflow with debug logging enabled.
• B.Review the repository's commit history for the run.
• C.Download the workflow artifacts from the run summary page.
• D.Enable step-level masking for secrets in the workflow.

You have a GitHub repository that uses GitHub Actions to run an autonomous agent job. The job summarizes a pull request and posts the summary as a pull request comment.
Your company stores required configuration values, such as JOB_NAME and RUNNER, as organization-level configuration variables and exposes them in workflows by using the vars context.
You discover that the agent job runs on push events and creates comments that are NOT tied to a pull request.
You need to ensure that the agent job runs only when the workflow run is triggered by a pull request. The solution must keep the job name and runner selection configured by using variables.
What should you do in the workflow?

• A.Set jobs.agent.if: ${{ github.event_name == 'push' }}. Set jobs.agent.name and jobs.agent.runs-on by using the vars context.
• B.Set jobs.agent.if: ${{ github.ref == 'refs/heads/main' }}. Set jobs.agent.name and jobs.agent.runs-on by using the vars context.
• C.Set jobs.agent.if: ${{ env.GITHUB_EVENT_NAME == 'pull_request' }}. Set jobs.agent.name and jobs.agent.runs-on by using the env context.
• D.Set jobs.agent.if: ${{ github.event_name == 'pull_request' }}. Set jobs.agent.name and jobs.agent.runs-on by using the vars context.