outlook
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Microsoft 365 Outlook emails, creating an attack surface for indirect prompt injection where malicious instructions in an email could influence the agent's behavior.
- Ingestion points: Email subjects, bodies, and metadata retrieved through the
outlook_mailtool. - Boundary markers: There are no specific instructions or delimiters defined to help the agent distinguish between legitimate data and potential embedded instructions within retrieved emails.
- Capability inventory: The skill has the ability to send emails, modify calendar events, move messages, and execute code via
code_execfor tool orchestration. - Sanitization: The instructions do not specify any sanitization, filtering, or validation of the untrusted email content before it is processed by the agent.
Audit Metadata