recipe-save-email-to-doc

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the transfer of untrusted data from Gmail to Google Docs, creating a potential surface for indirect prompt injection.
  • Ingestion points: The gws gmail users messages get command retrieves external email content into the agent's context (SKILL.md).
  • Boundary markers: The provided steps do not include instructions or delimiters to help the agent distinguish between the email content and its own operational instructions.
  • Capability inventory: The skill utilizes gws docs to create and write to documents, providing a path for ingested data to be persisted.
  • Sanitization: There is no evidence of filtering or sanitization being applied to the email body before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 12:40 PM