gws-gmail-send
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gwscommand-line tool, which is a vendor-owned resource for Google Workspace operations. This is the intended behavior of the skill. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes arbitrary text in the email body.
- Ingestion points: The
--bodyflag in thegws gmail +sendcommand accepts user-defined or externally-sourced text. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the body text are provided.
- Capability inventory: The skill has the capability to perform network operations (sending emails) via the
gwsbinary. - Sanitization: No specific sanitization or escaping mechanisms for the email body content are mentioned, although the tool handles standard RFC 2822 formatting.
Audit Metadata