The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the 'gws' command-line utility to perform administrative tasks like listing forms and fetching responses. These operations are consistent with the vendor's provided infrastructure for Google Workspace.
[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing untrusted data from Google Form responses. Ingestion points: Data enters the agent's context through the 'gws forms forms responses list' command output. Boundary markers: There are no explicit markers or instructions to isolate or ignore potentially malicious content within the form responses. Capability inventory: The skill utilizes commands to read form data and metadata. No destructive capabilities (e.g., file writes, arbitrary code execution) are explicitly defined in this recipe. Sanitization: The recipe does not include steps to sanitize or validate the content of the responses before they are presented to or processed by the agent.

recipe-collect-form-responses