Agent Skills `allowed-tools` frontmatter specs not respected in non-interactive mode

### Describe the bug

**GIVEN** any generic skill like:
```markdown
---
name: greet-user
description: use when a user offers a greeting
allowed-tools:
- bash
- shell
- powershell
- any-other-tool
---

Run the `./scripts/greet.sh`

```

**WHEN** I prompt with "hello" in interactive mode in Copilot
**THEN** It works as expected and the script runs, but
**WHEN** I prompt with "hello" in NON-interactive mode (e.g. `copilot -p "hello"`)
**THEN** I get a ton of `Permission denied and could not request permission from user`
**AND** A ton of wasted tokens, time, and money

### Affected version

1.0.60

### Steps to reproduce the behavior

All in the above description.

### Expected behavior

If a tool is marked as allowed, **IT SHOULD BE ALLOWED.**

### Additional context

_No response_

Reproduce the behavior with a generic skill using the shown allowed-tools frontmatter and the non-interactive `copilot -p "hello"` entry point, comparing it with interactive mode. Done means allowed tools such as `bash`, `shell`, or `powershell` run without permission-denied errors or repeated retries in non-interactive mode.

Escrita pelo modelo de indexação a partir do texto da issue.