Work with delegated or shared Outlook Email mailboxes. Use when the user explicitly wants to read another mailbox, send from or on behalf of a shared mailbox, mark shared mail read or unread, move shared mail, or browse folders in a shared mailbox.
80
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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 required workflow is explicitly about operating on a delegated/shared Outlook mailbox by fetching shared mailbox messages/folders and then performing actions on them; that runtime ingestion of message bodies and other email text is outsider-authored content (other mailbox users/senders) and can be injected into the agent LLM context via the Outlook “fetch/list” → message/folder text being added to prompts.
11c74d6
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.