microsoft-teams-automation
Warn
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill requires connecting to an external, unverified MCP server at https://rube.app/mcp. This server acts as a proxy for Microsoft Teams operations. Since the provider is not a known trusted organization, the security of the tool execution environment cannot be verified.
- PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection. It retrieves data from Microsoft Teams messages which may contain malicious instructions that the agent could inadvertently follow. 1. Ingestion points: MICROSOFT_TEAMS_SEARCH_MESSAGES and MICROSOFT_TEAMS_GET_CHAT_MESSAGE tools. 2. Boundary markers: None. No instructions are provided to the agent to distinguish between data and commands. 3. Capability inventory: Sending messages, managing team members, and creating meetings. 4. Sanitization: None. The skill does not describe any filtering or escaping of retrieved message content.
Audit Metadata