gws-events
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to wrap the
gwscommand-line utility, executing it with various resources and methods to manage Google Workspace events. This is the core functionality and is used within the intended scope of the tool. - [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data sources in Google Workspace, creating a surface where the agent could ingest data containing embedded instructions.
- Ingestion points: Data enters the agent context through event streams, task updates, and subscription details fetched via
message.stream,tasks.subscribe, andsubscriptionsresources. - Boundary markers: The analyzed file does not explicitly define delimiters for external data.
- Capability inventory: The skill has the ability to manage Workspace resources, including creating, deleting, and modifying subscriptions and tasks via the
gwsbinary. - Sanitization: There is no mention of explicit sanitization or filtering of the ingested Workspace data in this file.
Audit Metadata