Hello WorldSAFE
Agent Package Manager
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An APM (Agent Package Manager) application with comprehensive primitives compilation examples.
Quick Start
# Install dependencies apm install # Compile APM context into AGENTS.md apm compile # Run the hello world prompt apm run start --param name="" # Run feature implementation workflow apm run feature --param feature_name="User Authentication" --param feature_description="Implement secure user login and registration" # Preview before execution apm preview --param name=""
APM context Compilation
This project demonstrates the full APM context system:
Available Primitives
- Chatmodes:
default,backend-engineer - Instructions: TypeScript, Python, Testing guidelines
- Context: Project information, Architecture guidelines
For specification-driven development, consider using Spec-kit alongside APM for complete SDD workflows combined with advanced context management.
Compilation Commands
# Compile all primitives into AGENTS.md apm compile # Watch for changes and auto-recompile apm compile --watch # Validate primitives without compiling apm compile --validate # Dry run to preview output apm compile --dry-run # Use specific chatmode apm compile --chatmode backend-engineer
Directory Structure
.apm/ ├── chatmodes/ │ ├── default.chatmode.md │ └── backend-engineer.chatmode.md ├── instructions/ │ ├── typescript.instructions.md │ ├── python.instructions.md │ └── testing.instructions.md └── context/ ├── project-info.context.md └── architecture.context.md
Available Workflows
hello-world.prompt.md- Basic hello world demonstrationfeature-implementation.prompt.md- Implement features with validation gates
About
This project was created with APM - The package manager for AI-Native Development.
Learn more at: https://github.com/microsoft/apm
2ea90c57fbfcOBSERVED · 2026-10-08Install
Commands as the repository documents them. They are shown, not run.
npm install
pip install -r requirements.txt
Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| codex | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: {{project_name}}
description: {{description}}
---
# {{project_name}}
{{description}}
## What This Package Does
This is a starter APM package that demonstrates how to create reusable agent primitives.
## Getting Started
```bash
apm install your-org/{{project_name}}
apm compile
```
## Available Primitives
- **Instructions**: Guardrails and standards in `.apm/instructions/`
- **Prompts**: Executable workflows in `.apm/prompts/`
- **Agents**: Specialized personas in `.apm/agents/`
## Included Workflows
- `hello-world.prompt.md` - A simple hello world workflow
- `feature-implementation.prompt.md` - A feature implementation workflowTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
2ea90c57fbfcfull audit observations/trust-audit/skill/microsoft__hello-world.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 2ea90c57fbfc | SAFE | B | 89 | first audit |
Questions
What does the Hello World skill do?
Agent Package Manager
Is Hello World safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Hello World access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Hello World work with?
Its documentation mentions codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (2ea90c57fbfc), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.