outlook-cli
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses PowerShell COM objects (Outlook.Application) to interact with the local Microsoft Outlook application. This grants the agent the ability to perform operations within the user's mail environment.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external, untrusted sources (incoming emails and calendar events).
- Ingestion points: Data is read from $inbox.Items and $calendar.Items as defined in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to separate untrusted email content from agent instructions.
- Capability inventory: The skill possesses the capability to send emails using the $mail.Send() method.
- Sanitization: There is no evidence of content filtering or sanitization of the data retrieved from Outlook before it is processed.
Audit Metadata