gws-forms
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Google Forms, which represents a potential injection surface.
- Ingestion points: The skill retrieves data through methods such as 'gws forms get' and 'gws forms responses' defined in SKILL.md.
- Boundary markers: There are no delimiters or instructions provided to the agent to distinguish between tool instructions and data content within the forms.
- Capability inventory: The agent has the capability to modify form structures and settings using 'batchUpdate', 'create', and 'setPublishSettings'.
- Sanitization: No sanitization or validation of the retrieved form content is described before the agent processes it.
Audit Metadata