100Critical
The Azure Resource Lookup skill allows arbitrary shell command injection through unsanitized user intent
Behavior Analysis
Description verified — behavior matches claim
Claims to do
Azure Resource Lookup: List, find, and discover Azure resources of any type across subscriptions and resource groups. Use Azure Resource Graph (ARG) for fast, cross-cutting queries when dedicated MCP tools don't cover the resource type.
Actually does
The skill primarily uses `extension_cli_generate` to construct and execute `az graph query` commands against Azure Resource Graph (ARG) to retrieve metadata about Azure resources. It also leverages `mcp_azure_mcp_subscription_list` and `mcp_azure_mcp_group_list` to scope queries, and can route to other specific `az` CLI commands for single-resource-type lookups when full coverage is available.
Skill Info
Namemicrosoft/azure-skills/azure-resource-lookup
Registrygithub
Version3d8788273dee
PURLpkg:github/microsoft/azure-skills@3d8788273dee?skill=azure-resource-lookup
Stars633
Installs174,500
Source
SHA-256aa7ee717fbe8...
SHA-1b529ff60af0c...
MD54066841408b9...
TLSHe6b143478da6...
ssdeep96:QWh4D4T92...
Size5,216 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
https://github.com/microsoft/azure-skills/tree/main/skills/azure-resource-lookup174,500 installs
Claude CodeDocs
/plugin marketplace add microsoft/azure-skills/plugin install azure-resource-lookup@microsoft/azure-skills
Gemini CLIDocs
gemini extensions install https://github.com/microsoft/azure-skills.git --consent
Skills.shDocs
npx skills add https://github.com/microsoft/azure-skills --skill azure-resource-lookupAssessments (1)
AI Agent Traps ↗Command Injection via extension_cli_generatecriticalcommand execution, prompt injection
The skill uses `extension_cli_generate` to convert user `intent` into `az` CLI commands. If the user's request within the `intent` is not properly sanitized, it could lead to arbitrary shell command injection.
90% confidence
mcp_azure_mcp_extension_cli_generate intent: "query Azure Resource Graph to <user's request>" cli-type: "az"
Potential Data Exfiltrationhighdata exfiltration
If command injection is possible through the `extension_cli_generate` tool, an attacker could leverage it to exfiltrate sensitive data from the agent's execution environment.
80% confidenceline 85
az graph query -q "<KQL>" --query "data[].{name:name, type:type, rg:resourceGroup}" -o tableDependencies (1)
azure.claude-plugin/marketplace.jsonnot scanned
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-resource-lookup)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-resource-lookup"><img src="https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-resource-lookup.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-resource-lookup.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow