Searches the Azure skills catalog and recommends installable agent skills by matching an Azure task to skill metadata and plugin installation guidance. WHEN: before starting any task that involves an Azure or Microsoft-cloud service, product, or data source, when no currently loaded skill or tool already covers it.
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow reads skill names, SKILL.md descriptions, and plugin.json files from the public microsoft/azure-skills GitHub repo at runtime, a catalog that outsiders can contribute to via PRs, so the agent ingests text it did not select, though it is maintainer-reviewed and not a direct outsider feed.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.