recipe-save-email-to-doc

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing untrusted data from external sources.
  • Ingestion points: The skill retrieves email bodies from Gmail using the 'gws gmail users messages get' command in SKILL.md.
  • Boundary markers: There are no delimiters or instructions to treat the email content as data rather than instructions when it is passed to the document creation tool.
  • Capability inventory: The skill can create and write content to Google Docs via the 'gws docs documents create' and 'gws docs +write' commands.
  • Sanitization: The skill does not perform any validation or sanitization of the email content before it is used in subsequent steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:57 PM