gws-forms
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gwsCLI to interact with the Google Forms API. This utility is a vendor-owned resource intended for Workspace management. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting untrusted data from external form definitions and user-submitted responses.
- Ingestion points: Data is ingested into the agent context via the
forms.getandforms.responsesresources. - Boundary markers: No explicit delimiters or instructions are used to separate untrusted form content from the agent's instructions.
- Capability inventory: The skill allows the agent to create and update forms through the
createandbatchUpdatemethods. - Sanitization: The skill does not define any sanitization, validation, or escaping of the content retrieved from form resources.
Audit Metadata