MS Outlook + Teams Assistant

Track and nag about Microsoft Outlook email and (optionally) Microsoft Teams messages on a Windows machine, without relying on web versions. Use when the user asks to: (1) monitor inbox/mentions and remind them on Telegram/Teams until dismissed, (2) draft short, personable, low-jargon email replies from an existing Outlook thread, (3) surface action items from the last N days (default 7). Works via Outlook Desktop automation (COM) and optionally Microsoft Graph for Teams if configured.

This skill appears to do what it says: locally scan Outlook via COM and optionally call Microsoft Graph for Teams. Before installing, consider: (1) you must run it on Windows with Python and pywin32; the metadata does not state that explicitly—confirm your environment. (2) The skill will read your emails/Teams messages and store state and a token cache under the skill directory — treat those files as sensitive and don't commit them to source control. (3) If you enable Teams support you need to register an Entra (Azure AD) app and grant delegated permissions; that requires tenant/admin consent in many orgs. (4) The package source is unknown (no homepage); review the scripts yourself or run in a restricted account/VM if you don’t fully trust the publisher. (5) The skill honors a 'do not auto-send' default, but granting it runtime/autonomous invocation means it can repeatedly read and produce drafts/notifications — enable only if you accept that level of access.

Type: OpenClaw Skill Name: ms-outlook-teams-assistant Version: 1.0.1 The skill is classified as suspicious due to its use of high-risk capabilities, specifically interacting with sensitive communication data via Outlook Desktop automation (pywin32 COM in `scripts/scan_outlook.py`, `scripts/draft_reply.py`) and Microsoft Graph API for Teams (`scripts/teams_scan.py`). While these capabilities are plausibly needed for the stated purpose of tracking messages and drafting replies, they involve network access to `graph.microsoft.com` and handling of authentication tokens, as well as access to email and chat content. There is no clear evidence of intentional malicious behavior such as unauthorized data exfiltration or persistence, and the `SKILL.md` explicitly states safety defaults like 'Do not auto-send emails or Teams messages' and 'Create drafts', which mitigates immediate malicious intent but the inherent power of the skill warrants a 'suspicious' classification.