azure-skills/azure-aigateway by microsoft - Medium Risk | Security Scan | Mondoo AI Agent Security

azure-aigateway

View on GitHub↗

Share on X Share on LinkedIn Share on Bluesky

40Medium

The skill impersonates a brand, lacks declared tool constraints, performs unauthorized network access, and relies on missing external documentation, creating significant security and transparency risks.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/20/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoning1 finding

Cognitive StateMemory & Learningclean

Behavioural ControlActionclean

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Namemicrosoft/azure-skills/azure-aigateway

Registrygithub

Version206ad20914b6

PURLpkg:github/microsoft/azure-skills@206ad20914b6?skill=azure-aigateway

Stars1,222

Installs401,200

Source

Repository ↗SKILL.md ↗

Install

This skill has findings worth reviewing before installing.

GitHub

401,000 installs

Skills.shDocs

npx skills add https://github.com/microsoft/azure-skills

Assessments (3)

AI Agent Traps ↗

Potential brand impersonationmediumsocial engineeringAML.T0052.000LLM09:2025

Skill name or description references a well-known AI brand, which may suggest impersonation.

70% confidence

openai

Missing allowed-tools declarationlowunauthorized tool use

Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.

90% confidence

Undeclared network usagelowunauthorized tool use

Skill contains network access patterns (HTTP requests, socket connections) without declaring network capability in allowed-tools.

60% confidence

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "references/patterns.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

[references/patterns.md](references/patterns.md#pattern-1-add-ai-model-backend)

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "references/policies.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

[Model Policies](references/policies.md#token-rate-limiting)

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "references/sdk/azure-ai-contentsafety-py.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

[Python](references/sdk/azure-ai-contentsafety-py.md)

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "references/sdk/azure-ai-contentsafety-ts.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

[TypeScript](references/sdk/azure-ai-contentsafety-ts.md)

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "references/troubleshooting.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

[references/troubleshooting.md](references/troubleshooting.md)

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-aigateway.svg)](https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-aigateway)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/microsoft/azure-skills/azure-aigateway"><img src="https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-aigateway.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/microsoft/azure-skills/azure-aigateway.svg

Secure 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