outlook
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill is installed from an external source (refly.ai) using a custom CLI tool, which is not included in the trusted provider list.
- COMMAND_EXECUTION (LOW): The skill executes local commands including
refly,jq, andopento perform its primary functions. - PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection as it processes external input for email and calendar actions. 1. Ingestion points: Input JSON fields
recipient_email,email_subject, andemail_bodyinSKILL.md. 2. Boundary markers: Absent; no delimiters are used to separate untrusted data from instructions. 3. Capability inventory: The skill can send emails and create calendar events usingrefly skill run. 4. Sanitization: No sanitization or validation of the input data is documented.
Audit Metadata