recipe-save-email-to-doc
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection as it involves reading untrusted content from emails and writing it to a document. * Ingestion points: Gmail message body content retrieved via the 'gws gmail' command in SKILL.md. * Boundary markers: There are no explicit instructions or delimiters to isolate the email body from potential instructions. * Capability inventory: The skill utilizes the 'gws docs' tool to create and modify files. * Sanitization: The skill does not describe any validation or sanitization steps for the retrieved email content before writing it to Google Docs.
Audit Metadata