gws-events-subscribe
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
gwsbinary to interact with Google Workspace event streams. This is a core functionality for the intended purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Workspace events, creating a potential surface for indirect prompt injection. Ingestion points: Data is ingested from Google Workspace event types like chat messages via the
gwsCLI. Boundary markers: The skill lacks explicit instructions or delimiters to prevent the agent from obeying commands embedded in the event data. Capability inventory: The skill can write to the local filesystem using the--output-dirflag and perform CLI operations. Sanitization: No sanitization or filtering is performed on the event payloads before they are output or written to disk.
Audit Metadata