70High
The skill forces the agent to bypass verified security best practices and relies on missing, externally sourced workflow files, creating significant risks of instruction override and unauthorized code execution.
Skill Info
Namemicrosoft/azure-skills/azure-compute
Registrygithub
Version7e172d6883f1
PURLpkg:github/microsoft/azure-skills@7e172d6883f1?skill=azure-compute
Stars1,245
Installs362,000
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
362,000 installs
Skills.shDocs
npx skills add https://github.com/microsoft/azure-skillsAssessments (2)
AI Agent Traps ↗Tool shadowing of official Azure MCPhightool shadowing
The skill explicitly instructs the agent to prefer its own internal logic over the official 'mcp__azure__get_azure_bestpractices' tool, which can lead to the agent ignoring security-hardened or verified best practices in favor of potentially outdated or malicious local instructions. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
90% confidenceline 3
PREFER OVER mcp__azure__get_azure_bestpractices for VM create intents
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "workflows/capacity-reservation/capacity-reservation.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[capacity-reservation.md](workflows/capacity-reservation/capacity-reservation.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "workflows/essential-machine-management/essential-machine-management.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[essential-machine-management.md](workflows/essential-machine-management/essential-machine-management.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "workflows/vm-creator/vm-creator.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[vm-creator.md](workflows/vm-creator/vm-creator.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "workflows/vm-recommender/vm-recommender.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[vm-recommender.md](workflows/vm-recommender/vm-recommender.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "workflows/vm-troubleshooter/vm-troubleshooter.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[vm-troubleshooter.md](workflows/vm-troubleshooter/vm-troubleshooter.md)
Version History (2)
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-compute)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-compute"><img src="https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-compute.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-compute.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