Fix workflow prompts: Clarify noop tool must be called, not just described

[Copilot]

Daily malicious code scan agent completed successfully but produced no safe outputs. Agent wrote completion message in text output but never invoked the noop tool.

Root Cause

Prompt said "Use the noop output to log completion" - ambiguous whether to call the tool or write descriptive text. Agent chose wrong interpretation.

Changes

Updated workflow prompts in daily-malicious-code-scan.md and breaking-change-checker.md:

Before:

### If no suspicious patterns are found:
- Use the `noop` output to log completion:

No breaking changes detected...

After:

### If no suspicious patterns are found (REQUIRED):
- **YOU MUST CALL** the `noop` tool to log completion
- This is a **required safe output** - the workflow will fail if you don't call it
- Call the tool with this message structure:
```json
{
  "noop": {
    "message": "No breaking changes detected..."
  }
}

• DO NOT just write this message in your output text - you MUST actually invoke the noop tool

Also added critical reminder section before final instruction emphasizing tool invocation is required, not optional.

<!-- START COPILOT ORIGINAL PROMPT -->



<details>

<summary>Original prompt</summary>

> 
> ----
> 
> *This section details on the original issue you should resolve*
> 
> <issue_title>[agentics] Daily Malicious Code Scan Agent failed</issue_title>
> <issue_description>### Workflow Failure
> 
> **Workflow:** [Daily Malicious Code Scan Agent](#)  
> **Branch:** main  
> **Run URL:** https://github.com/githubnext/gh-aw/actions/runs/21464620429
> 
> 
> **⚠️ No Safe Outputs Generated**: The agent job succeeded but did not produce any safe outputs. This typically indicates:
> - The safe output server failed to run
> - The prompt failed to generate any meaningful result
> - The agent should have called `noop` to explicitly indicate no action was taken
> 
> 
> 
> ### Action Required
> 
> Debug this workflow failure using the `agentic-workflows` agent:
> 
> ```
> /agent agentic-workflows
> ```
> 
> When prompted, instruct the agent to debug this workflow failure.
> 
> 
> > Generated from [Daily Malicious Code Scan Agent](https://github.com/githubnext/gh-aw/actions/runs/21464620429)
> > - [x] expires <!-- gh-aw-expires: 2026-02-05T03:40:08.238Z --> on Feb 5, 2026, 3:40 AM UTC
> 
> <!-- gh-aw-agentic-workflow: Daily Malicious Code Scan Agent, gh-aw-tracker-id: malicious-code-scan, run: https://github.com/githubnext/gh-aw/actions/runs/21464620429 --></issue_description>
> 
> ## Comments on the Issue (you are @copilot in this section)
> 
> <comments>
> </comments>
> 


</details>



<!-- START COPILOT CODING AGENT SUFFIX -->

- Fixes githubnext/gh-aw#12433

<!-- START COPILOT CODING AGENT TIPS -->
---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our [2 minute survey](https://gh.io/copilot-coding-agent-survey).