outlook-automation

Warn

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external MCP server endpoint (https://rube.app/mcp). This is a community-provided infrastructure that acts as a proxy between the agent and Microsoft Graph APIs.
  • [DATA_EXFILTRATION]: The skill is designed to read, search, and manage sensitive communications and personal data, including email bodies, attachments, and contact lists. This data is processed through the third-party rube.app service, which represents a significant trust requirement as the service handles the OAuth tokens and data flow.
  • [PROMPT_INJECTION]: The skill provides tools to ingest untrusted data from external sources, specifically through OUTLOOK_GET_MESSAGE and OUTLOOK_DOWNLOAD_OUTLOOK_ATTACHMENT. This creates a surface for indirect prompt injection, where an attacker could send a malicious email containing instructions designed to hijack the agent's session. The skill lacks boundary markers or sanitization logic to mitigate this risk.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 06:26 PM