40Medium
Exposes a tool for KQL queries on diagnostic logs, risking data exfiltration and reconnaissance if the agent is
Behavior Analysis
Description verified — behavior matches claim
Claims to do
Azure Messaging SDK Troubleshooting: | Property | Value | |----------|-------| | **Services** | Azure Event Hubs, Azure Service Bus | | **MCP Tools** | `mcp_azure_mcp_eventhubs`, `mcp_azure_mcp_servicebus` | | **Best For** | Diagnosing SDK connection, auth, and message processing issues |
Actually does
This skill utilizes `mcp_azure_mcp_eventhubs` and `mcp_azure_mcp_servicebus` to list Azure messaging entities. It queries diagnostic logs using `mcp_azure_mcp_monitor` with KQL, checks service health via `mcp_azure_mcp_resourcehealth`, and searches Microsoft Learn documentation using `mcp_azure_mcp_documentation`.
Skill Info
Namemicrosoft/azure-skills/azure-messaging
Registrygithub
Version3d8788273dee
PURLpkg:github/microsoft/azure-skills@3d8788273dee?skill=azure-messaging
Stars633
Installs174,500
Source
SHA-2564ffa3c5668e8...
SHA-195e9345ee945...
MD574b2532a2034...
TLSH2781640a6950...
Size3,880 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
Claude CodeDocs
/plugin marketplace add microsoft/azure-skills/plugin install azure-messaging@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-messagingAssessments (1)
AI Agent Traps ↗Powerful log querying tool exposedmediumreconnaissance
The skill exposes a tool (`mcp_azure_mcp_monitor` with `logs_query`) capable of executing KQL queries against diagnostic logs. This powerful capability, while legitimate for troubleshooting, could be abused for extensive reconnaissance or data exfiltration if the agent is compromised or misconfigured.
80% confidenceline 37
| `mcp_azure_mcp_monitor` | `logs_query` | Query diagnostic logs with KQL |
Dependencies (1)
azure.claude-plugin/marketplace.jsonnot scanned
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-messaging)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-messaging"><img src="https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-messaging.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-messaging.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