microsoft-teams-automation

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to connect to an external MCP server located at https://rube.app/mcp. This third-party endpoint provides the necessary tools for Microsoft Teams automation and represents a remote dependency outside of the trusted vendor list.\n- [PROMPT_INJECTION]: The skill provides a significant surface for indirect prompt injection as it processes untrusted data from an external environment.\n
  • Ingestion points: Untrusted data enters the agent context via tools like MICROSOFT_TEAMS_SEARCH_MESSAGES and MICROSOFT_TEAMS_GET_CHAT_MESSAGE as defined in SKILL.md.\n
  • Boundary markers: The skill body contains no specific boundary markers or instructions (e.g., delimiters or 'ignore' commands) to prevent the agent from executing instructions embedded within retrieved messages.\n
  • Capability inventory: The skill has extensive capabilities including posting channel messages (MICROSOFT_TEAMS_TEAMS_POST_CHANNEL_MESSAGE), creating chats (MICROSOFT_TEAMS_TEAMS_CREATE_CHAT), adding members to teams (MICROSOFT_TEAMS_ADD_MEMBER_TO_TEAM), and creating meetings (MICROSOFT_TEAMS_CREATE_MEETING).\n
  • Sanitization: There is no mention or implementation of sanitization, validation, or escaping of the external content before it is interpolated into the agent's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:32 PM