recipe-save-email-attachments
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external sources (Gmail emails and attachments), which may contain instructions intended to influence the agent's behavior.
- Ingestion points: External data enters the context via the
gws gmail users messages listandgws gmail users messages getcommands in SKILL.md. - Boundary markers: The skill does not provide specific delimiters or instructions for the agent to distinguish between the workflow instructions and the content of the emails being processed.
- Capability inventory: The skill uses the
gwsbinary to list messages, retrieve message details, download files to the local file system, and upload files to Google Drive, as described in SKILL.md. - Sanitization: No sanitization, filtering, or validation steps are defined to inspect the email content before the agent processes it.
Audit Metadata