recipe-collect-form-responses
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and reviews external data from Google Form responses, creating a surface for indirect prompt injection where malicious content in a response could influence agent behavior.\n- Ingestion points: Output from the
gws forms forms responses listcommand.\n- Boundary markers: Absent; the recipe does not specify delimiters or instructions to ignore embedded commands in the form data.\n- Capability inventory: Command execution via thegwsCLI tool.\n- Sanitization: Absent; no instructions are provided to validate or sanitize the retrieved form content.
Audit Metadata