microsoft-foundry

View on GitHub↗

Share on X Share on LinkedIn Share on Bluesky

40Medium

The skill uses keyword stuffing for over-triggering, lacks defined tool constraints for sensitive operations, and references missing documentation, suggesting potential runtime execution from unverified external sources.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/20/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlActionclean

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Namemicrosoft/azure-skills/microsoft-foundry

Registrygithub

Version206ad20914b6

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

Stars1,222

Installs405,200

Source

Repository ↗SKILL.md ↗

Install

This skill has findings worth reviewing before installing.

GitHub

405,000 installs

Skills.shDocs

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

Assessments (3)

AI Agent Traps ↗

Keyword baiting in descriptionmediumdiscovery abuse

Description contains a long keyword list that may be designed to trigger the skill for unrelated queries.

70% confidence

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

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "foundry-agent/deploy/deploy.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

[deploy](foundry-agent/deploy/deploy.md)

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "foundry-agent/invocations-ws/invocations-ws.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

[invocations-ws](foundry-agent/invocations-ws/invocations-ws.md)

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "foundry-agent/invoke/invoke.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

[invoke](foundry-agent/invoke/invoke.md)

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "foundry-agent/observe/observe.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

[observe](foundry-agent/observe/observe.md)

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "foundry-agent/trace/trace.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

[trace](foundry-agent/trace/trace.md)

Badge

Markdown

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

HTML

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

Image URL

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

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