gws-events
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for using the
gwscommand-line tool to interact with Google Workspace resources such as messages, operations, subscriptions, and tasks. It includes usage patterns for resource methods likecreate,delete,list, andpatch. - [EXTERNAL_DOWNLOADS]: The skill metadata references source code and documentation hosted on the official Google Workspace GitHub organization repository (
googleworkspace/cli), which is a well-known service. - [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface by processing external data:
- Ingestion points: Event streams, task updates, and subscription details retrieved via
gws eventscommands (SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are defined in the provided file.
- Capability inventory: The agent can execute
gwscommands for managing subscriptions and inspecting API schemas (SKILL.md). - Sanitization: There are no explicit sanitization or validation steps described for the data returned by the API before it is processed by the agent.
Audit Metadata