outlook-automation

Warn

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to configure an external MCP server endpoint at 'https://rube.app/mcp'. This domain is not identified as a trusted organization or well-known service in the provided list, and it does not match the vendor resource patterns for 'sickn33'.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its interaction with Microsoft Outlook data.
  • Ingestion points: Content is retrieved from external emails using the OUTLOOK_GET_MESSAGE and OUTLOOK_SEARCH_MESSAGES tools defined in SKILL.md.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are specified for processing email bodies.
  • Capability inventory: The agent is granted permissions to read, search, and modify sensitive emails, contacts, and calendar entries.
  • Sanitization: No sanitization or validation of the external email content is implemented to prevent the agent from acting on malicious instructions embedded in message bodies.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:11 AM