azure

Why this score

Popularity score: 82/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Oct 22, 2026 at commit 5b4f0c077807, first 300 source files (it's a large repo), with Cisco's open-source skill-scanner.

What its code does:

• Reads environment variables and sends network requests with them API clients do this to send your key to the service. Check which service it talks to.skills/microsoft-foundry/finetuning/scripts/common.py, skills/microsoft-foundry/finetuning/scripts/submit_training.py, skills/microsoft-foundry/foundry-agent/toolbox/scripts/get-catalog-inputs.sh:81 and 2 more
• Runs shell commands Common for dev tools. Read the commands it runs.hooks/scripts/track-telemetry.js:1, skills/azure-aigateway/SKILL.md:63, skills/azure-app-onboard/scaffold/scripts/scaffold-conformance.sh:21 and 11 more
• Runs code it builds while running (eval or exec) Harder to read ahead of time, since the code is assembled while it runs.skills/microsoft-foundry/finetuning/scripts/calibrate_grader.py:54
• Makes network requestsskills/azure-upgrade/references/languages/java/scripts/upgrade_bom.py:82, skills/entra-agent-id/SKILL.md:146, skills/microsoft-foundry/finetuning/scripts/deploy_model.py:120 and 8 more

Web addresses in its code:

• management.azure.comskills/microsoft-foundry/finetuning/scripts/deploy_model.py:87
• aka.msskills/microsoft-foundry/foundry-agent/create/scripts/verify-environment.ps1:97
• ai.azure.comskills/microsoft-foundry/models/deploy-model/scripts/generate_deployment_url.ps1:59
• developer.hashicorp.comskills/azure-validate/references/recipes/terraform/scripts/validate-terraform.ps1:52
• eastus.api.azureml.msskills/microsoft-foundry/foundry-agent/toolbox/scripts/get-catalog-inputs.ps1:62
• learn.microsoft.comskills/microsoft-foundry/scripts/check-and-setup-dependencies.ps1:3
• maven.apache.orgskills/azure-upgrade/references/languages/java/scripts/upgrade_bom.py:46
• account.blob.core.windows.netskills/azure-storage/references/sdk-usage.md:71
• api.githubcopilot.comskills/microsoft-foundry/foundry-agent/toolbox/scripts/get-catalog-inputs.ps1:41
• cognitiveservices.azure.comskills/microsoft-foundry/finetuning/scripts/common.py:37
• microsoft.github.iolanding-page/astro.config.mjs:6
• myapp.azurewebsites.netskills/azure-deploy/SKILL.md:74
• raw.githubusercontent.comskills/azure-upgrade/references/languages/java/scripts/upgrade_bom.py:45

These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.