teams-hack
Your agent reads Teams chats, posts to channels, searches everything. One stolen token. 90 days per browser tap.
Why use this skill?
Integrate OpenClaw with Microsoft Teams to manage chats, search messages, and sync calendars. Get 90 days of automated access with one simple token extraction.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/globalcaos/teams-hackWhat This Skill Does
The teams-hack skill is a powerful automation utility for OpenClaw that enables deep integration with Microsoft Teams. By extracting an MSAL refresh token, the agent gains persistent access to your organizational chat and collaboration workspace for up to 90 days. It functions by tapping into the localStorage of your browser session to harvest credentials, allowing the agent to perform actions as if it were a legitimate, authenticated user. Once active, the agent can read and send messages in 1:1 or group chats, post updates to team channels, search through your entire communication history, and query the organizational directory for contact information and presence status. It also integrates with your calendar to display meeting links, effectively turning the agent into a personal assistant for your professional workspace.
Installation
Installation is straightforward but requires one-time manual intervention to extract the session token. First, ensure you have the OpenClaw browser relay installed. Open Microsoft Teams in Chrome and navigate to the web application. While the page is loaded, execute the provided JavaScript snippet via the OpenClaw developer console to capture your refreshtoken and tenantId. Once retrieved, run teams token store --refresh-token <secret> --tenant-id <tenantId> in your terminal. You can confirm the successful linkage of your account by running the teams token test command. This process securely stores your credentials, enabling the agent to maintain session persistence without needing to log in repeatedly.
Use Cases
The skill is ideal for professionals seeking to automate administrative tasks or streamline communication. Use it to automatically summarize daily discussions in busy channels, track specific project updates across disparate conversations, or manage your calendar availability without switching contexts. It is particularly useful for developers or project managers who need to monitor team status or respond to routine queries quickly. Because it shares a token with the outlook-hack skill, it serves as a unified gateway for all Microsoft 365 communications, providing a cohesive interface to manage both email and chat streams simultaneously.
Example Prompts
- "Check the #project-alpha channel and summarize the latest updates from the team regarding the Q4 deadline."
- "Find the most recent message from Sarah regarding the budget approval and reply that I have reviewed it."
- "Do I have any meetings within the next hour? If so, provide the link and tell me who the organizer is."
Tips & Limitations
Note that this skill relies on the continued validity of the extracted MSAL refresh token. If you sign out of Teams globally, the token may be revoked. The skill works best when kept active through regular interaction, which helps prevent token expiration. Always exercise caution, as this skill grants the agent broad permissions within your organizational account. Ensure your local environment is secured, as the ~/.openclaw/credentials/outlook-msal.json file contains sensitive authentication data that should never be shared or committed to version control systems.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-globalcaos-teams-hack": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, data-collection, external-api
Related Skills
jarvis-voice
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
shell-security-ultimate
Classify every shell command as SAFE, WARN, or CRIT before your agent runs it.
memory-pioneer
Benchmark your agent's memory. Contribute anonymized scores to open research. Citizen science for AI memory.
subagent-overseer
Monitor sub-agent health and progress via a pull-based bash daemon. Use when spawning sub-agents that need progress tracking, staleness detection, and automatic status reporting. Replaces manual heartbeat polling with a deterministic status file the agent reads every 3 minutes. Zero AI tokens for monitoring — pure OS-level process checks and filesystem diffs.
model-router
Automatic LLM model selection for sub-agent tasks. Classifies tasks by complexity and type, then routes to the optimal model (cost vs capability). Use when spawning sub-agents, choosing models for cron jobs, or deciding which model to use for any task. Eliminates manual model specification by providing a decision tree and optional cheap-model classifier for ambiguous cases.