gws-gmail-triage
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from an external source, specifically Gmail inbox metadata.
- Ingestion points: The skill reads sender information and email subject lines from the user's Gmail account via the 'gws' command-line tool.
- Boundary markers: The instructions do not specify any delimiters or boundary markers to differentiate between system instructions and the untrusted email content fetched by the tool.
- Capability inventory: The skill is restricted to read-only operations for summarizing message headers and does not perform file writes or network exfiltration within the provided script context.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the email content before it is processed by the agent.
Audit Metadata