The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes commands using the gws binary to manage resources across Google Workspace.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from external sources.
Ingestion points: Untrusted data is ingested from Gmail messages, meeting summaries, and Drive files via helper commands like +email-to-task and +standup-report.
Boundary markers: The skill does not specify any boundary markers or instructions to ignore potential commands embedded within the ingested data.
Capability inventory: The skill uses the gws binary to perform read and write operations across various Google services.
Sanitization: There is no evidence of input validation or sanitization for the content retrieved from external sources before it is processed by the agent.

gws-workflow