recipe-save-email-to-doc
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data (email bodies) into the agent's context and other workspace tools.
- Ingestion points: Email messages are retrieved via the
gws gmail users messages getcommand inSKILL.md. - Boundary markers: None are defined; the recipe uses a direct interpolation of the email body into the document write command.
- Capability inventory: The skill involves reading Gmail data and writing to Google Docs.
- Sanitization: Not explicitly present in the instructional steps, although standard tool-level sanitization is expected during execution.
Audit Metadata