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 gws command-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 list command retrieves data from external Google Forms responses as shown in SKILL.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 gws CLI binary to interact with Workspace data.\n
  • Sanitization: Absent; there are no specified filters or sanitization steps for the retrieved response content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:57 PM