gws-chat
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gws(Google Workspace CLI) to interact with Google Chat APIs for resource management. - [DATA_EXFILTRATION]: Includes standard features for downloading and uploading media attachments within Google Chat, which aligns with the skill's management purpose.
- [PROMPT_INJECTION]: Presents a potential surface for indirect prompt injection as the agent processes external data from Chat messages and space metadata.
- Ingestion points: Retrieves message content, space names, and descriptions via the
gws chatcommand. - Boundary markers: The skill does not specify clear delimiters to isolate ingested chat data from agent instructions.
- Capability inventory: Possesses capabilities to modify space settings, manage memberships, and post messages.
- Sanitization: The skill does not explicitly define sanitization or validation logic for the content retrieved from Google Chat.
Audit Metadata