microsoft-foundry

microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent, managed harness agent, Copilot harness, voice agent, create/update/invoke/evaluate agent, add tool to agent, agent insights, batch/continuous eval, continuous monitoring, agent CI/CD, optimize/improve prompt, optimize agent instructions, Agent Optimizer, datas

The scanner found nothing risky in the 101 files we could read.

Repository skills.sh

What it does

Runs shell commands
Installs packages
Reaches 127.0.0.1, account.box.com, accounts.google.com, ai.azure.com, aka.ms, api.box.com, api.example.com, api.githubcopilot.com, app-xx, azure.microsoft.com, code.visualstudio.com, cognitiveservices.azure.com, developer.spotify.com, eastus.api.azureml.ms, example.com, github.com, global-test.consent.azure-apim.net, global.consent.azure-apim.net, go.microsoft.com, int.ai.azure.com, learn.microsoft.com, localhost, logic-apis, logic-apis-eastus.azure-apim.net, logic-apis-eastus.consent.azure-apim.net, login.microsoftonline.com, management.azure.com, my-account.services.ai.azure.com, oauth2.googleapis.com, placeholder, portal.azure.com, tools.example.com, workiq.svc.cloud.microsoft, www.microsoft.com, your-function-app.azurewebsites.net
Reads ACCOUNTS_FILE, ACCOUNTS_JSON, ACCOUNT_NAME, AGENT_NAME, AI_AGENT, API_KEY, AZURE_AI_MODEL_DEPLOYMENT_NAME, AZURE_AI_PROJECT_ENDPOINT, AZURE_COGSERVICES_ACCOUNT, AZURE_DEV_USER_AGENT, AZURE_OPENAI_API_KEY, AZURE_OPENAI_ENDPOINT, AZURE_RESOURCE_GROUP, AZURE_SUBSCRIPTION_ID, AZ_CLI_PATH, CONNECTION_NAME, COPILOT_CLI, COPILOT_CLI_EXTRACT_DIR, COPILOT_CLI_PATH, DEPLOYMENT_NAME, ENDPOINT, HOME, LASTEXITCODE, LOCALAPPDATA, MATCHED_ACCOUNT, MODEL_NAME, NORMALIZED_ENDPOINT, OPENAI_BASE_URL, OUTPUT, PARSED_ENDPOINT, PLUGIN_NAME, PLUGIN_SPEC, POLICY_NAME, PROJECTS_FILE, PROJECTS_JSON, PROJECT_ENDPOINT, PROJECT_JSON, PROJECT_NAME, REGION, RESOURCE_GROUP, SUBSCRIPTION, SUBSCRIPTION_ID, TOK, TOKEN, TWILIO_ACCOUNT_SID, TWILIO_AUTH_TOKEN, URL, XDG_CACHE_HOME, XDG_DATA_HOME
Writes $ACCOUNTS_FILE, $PROJECTS_FILE, $stderr_file, .consent.azure-apim.net/login, .openai.azure.com, .search.windows.net/, .services.ai.azure.com/api/projects/, /, /., /SKILL.md, /agents/, /api/projects/, /connections/, /endpoint/protocols/voice, /eval.yaml, /mcp, /openai/v1/, /projects/, /providers/Microsoft.CognitiveServices/accounts/, /raiPolicies/, /resourceGroups/, /toolboxes/, /v1/mcp/..., /versions/, 2.0, checkpoints.data

Findings (0)

The scanner found nothing risky in 101 files.

Some of the skill's files couldn't be read, so this check may be incomplete.

Decide which skills your team's agents may run

skillsvault scans every skill your organisation uses, blocks the ones you ban on every developer's machine, and keeps a tamper-evident record of every run. Free for one developer.

Add it to your registry Get started free

A deterministic scan of the skill's files as published today; it isn't a guarantee. It reads the files and reports what they do — nothing is run or installed.