The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the gws binary to perform resource management and schema lookups across Google Workspace services.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain adversarial instructions designed to influence agent behavior.
Ingestion points: Processes content from Gmail messages, Calendar agendas, and Google Drive files through its helper commands like +email-to-task and +meeting-prep.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill definitions.
Capability inventory: The skill possesses the ability to read from and write to Google Tasks, Chat, and other Workspace resources.
Sanitization: There is no evidence of filtering or sanitizing the retrieved external data before it is presented to the agent context.

gws-workflow