recipe-collect-form-responses
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gwscommand-line utility to perform administrative tasks on Google Forms, such as listing forms and retrieving response data. This behavior is aligned with the skill's primary function.\n- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data by reading responses from Google Forms, creating a potential surface for indirect prompt injection.\n - Ingestion points: The
gws forms forms responses listcommand retrieves data from external Google Forms responses as shown inSKILL.md.\n - Boundary markers: Absent; the skill does not provide specific delimiters or instructions to ignore potential commands embedded in form responses.\n
- Capability inventory: The skill has access to the
gwsCLI binary to interact with Workspace data.\n - Sanitization: Absent; there are no specified filters or sanitization steps for the retrieved response content.
Audit Metadata