gws-workflow-email-to-task
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted external data from Gmail (email subjects and snippets).
- Ingestion points: Gmail message content accessed via the
--message-idflag in thegwsCLI. - Boundary markers: The skill does not define specific delimiter boundaries or instructions to ignore embedded text in the email content, though it does include a tip to 'confirm with the user before executing' which mitigates unintended execution.
- Capability inventory: The skill uses the
gwsCLI tool to read email data and write/create task entries. - Sanitization: There are no explicit instructions for the agent to sanitize or escape the content retrieved from the email before processing it.
Audit Metadata