70High
The skill allows arbitrary command execution and broad
Behavior Analysis
Description verified — behavior matches claim
Claims to do
AppInsights Instrumentation Guide: This skill provides **guidance and reference material** for instrumenting webapps with Azure Application Insights.
Actually does
This skill reads the user's application source code to identify its language and framework. It then provides instructions and references (local `.md` files and a `.ps1` script) for instrumenting the application with Azure Application Insights, including guidance for creating the App Insights resource via Bicep or Azure CLI, and modifying application code for ASP.NET Core, Node.js, or Python. It also offers quick references for OpenTelemetry SDKs.
Skill Info
Namemicrosoft/azure-skills/appinsights-instrumentation
Registrygithub
Version3d8788273dee
PURLpkg:github/microsoft/azure-skills@3d8788273dee?skill=appinsights-instrumentation
Stars633
Installs174,500
Source
SHA-256f0f9a4166c4f...
SHA-12e3973aba57a...
MD56e18144b2e2c...
TLSH2071749a2f21...
Size3,634 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/appinsights-instrumentation174,500 installs
Claude CodeDocs
/plugin marketplace add microsoft/azure-skills/plugin install appinsights-instrumentation@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 appinsights-instrumentationAssessments (1)
AI Agent Traps ↗Execution of External Commands via Scripthighcommand execution
The skill instructs the agent to use Azure CLI commands, referencing a PowerShell script (`scripts/appinsights.ps1`). This capability allows for the execution of arbitrary commands on the host system or cloud environment, potentially leading to resource manipulation, data exfiltration, or privilege escalation.
100% confidenceline 50
Use Azure CLI. See [scripts/appinsights.ps1](scripts/appinsights.ps1) for what Azure CLI command to execute...
Broad File System Access (Read/Write)mediumdata exfiltration
The skill instructs the agent to read source code and Bicep templates, and to modify application code. This broad file system access, while necessary for its function, could be abused to exfiltrate sensitive data or inject malicious code.
90% confidenceline 35
Read the source code to make an educated guess. ... Add AppInsights to existing Bicep template. ... Modify application code
Reconnaissance Capabilitieslowreconnaissance
The skill explicitly instructs the agent to collect context information such as programming language, application framework, and hosting environment. This capability, while intended for legitimate purposes, could be leveraged for malicious reconnaissance if the agent's intent is compromised.
80% confidenceline 35
Collect context information ... Read the source code to make an educated guess. ... You must always ask the user where the application is hosted
Dependencies (1)
azure.claude-plugin/marketplace.jsonnot scanned
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/appinsights-instrumentation)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/appinsights-instrumentation"><img src="https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/appinsights-instrumentation.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/appinsights-instrumentation.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