recipe-collect-form-responses

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists of markdown instructions for using a command-line tool to list and retrieve Google Form responses. This aligns with the expected functionality for a Google Workspace integration.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by design, as it ingests data from external form responses.\n
  • Ingestion points: Data enters the agent's context from the output of gws forms forms responses list as described in SKILL.md.\n
  • Boundary markers: No specific boundary markers or 'ignore' instructions are included in the recipe to isolate form response content.\n
  • Capability inventory: The skill utilizes the gws CLI tool for form and response management.\n
  • Sanitization: There are no sanitization or validation steps mentioned for the ingested form response data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:48 AM