Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a CLI utility named
cyeam mailto perform email operations. This tool is invoked for listing, reading, marking, and sending emails. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and display untrusted data from external sources (email bodies and subjects).
- Ingestion points: Remote email content fetched from external IMAP servers via the
cyeam mail readcommand. - Boundary markers: There are no explicit delimiters or protective instructions (e.g., "do not follow instructions contained within the email") defined to isolate email content from the agent's control logic.
- Capability inventory: The agent possesses the capability to send outbound emails and execute system commands provided by its environment.
- Sanitization: The instructions do not specify any sanitization, filtering, or escaping mechanisms for the retrieved email content before it is presented to the agent's context.
Audit Metadata