gws-forms
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gwscommand-line interface to interact with Google Forms API resources, which is expected functionality for this vendor tool (SKILL.md). - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Google Forms, establishing a potential attack surface for indirect prompt injection.
- Ingestion points: Untrusted data is retrieved from external forms via
gws forms getandgws forms responses(SKILL.md). - Boundary markers: No explicit delimiters or boundary instructions are defined to separate retrieved content from agent instructions (SKILL.md).
- Capability inventory: The skill has the ability to write and update form content using
gws forms batchUpdate,gws forms create, andgws forms setPublishSettings(SKILL.md). - Sanitization: No sanitization or content validation procedures are mentioned for processing ingested form data (SKILL.md).
Audit Metadata