microsoft-teams-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the user to connect to an external MCP server at https://rube.app/mcp. This is a requirement for accessing the Composio Microsoft Teams toolkit and is consistent with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes untrusted data from Microsoft Teams messages.
  • Ingestion points: The agent retrieves external content using tools like MICROSOFT_TEAMS_SEARCH_MESSAGES and MICROSOFT_TEAMS_GET_CHAT_MESSAGE (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions for data retrieved from Teams.
  • Capability inventory: The skill possesses the ability to post messages to channels and chats, and to create calendar meetings.
  • Sanitization: No explicit sanitization or filtering of the retrieved message content is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — microsoft-teams-automation