recipe-collect-form-responses
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data by instructing the agent to list and review responses from a Google Form.
- Ingestion points: The output of the 'gws forms forms responses list' command described in 'SKILL.md'.
- Boundary markers: No delimiters or instructions to ignore potential commands within the form data are provided to the agent.
- Capability inventory: The agent uses the 'gws' CLI tool (defined in 'SKILL.md' metadata), which possesses capabilities for network interaction and data retrieval.
- Sanitization: No sanitization or content validation logic is applied to the retrieved form responses before they are processed by the agent.
Audit Metadata