The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the gws binary to execute commands for managing Google Forms resources, including batchUpdate, create, get, setPublishSettings, responses, and watches as documented in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from Google Forms which could contain malicious instructions designed to influence the agent.
Ingestion points: External data is ingested via the gws forms get and gws forms responses commands.
Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between data and instructions when reading form content.
Capability inventory: The skill's capabilities are limited to Google Forms API operations via the gws CLI tool.
Sanitization: There is no mention of sanitization, filtering, or validation of the content retrieved from form titles, descriptions, or response data.

gws-forms