gws-gmail-triage
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
gwsCLI tool. This is the primary intended function for interacting with the Gmail API via a local environment. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external source (Gmail inbox).
- Ingestion points: Reading unread email sender and subject lines.
- Boundary markers: None explicitly defined in this file to separate email content from agent instructions.
- Capability inventory: Limited to read operations and displaying output to the user.
- Sanitization: No specific sanitization or filtering of email content is described in the instruction set.
Audit Metadata