gws-forms
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gwscommand-line tool to interact with Google Workspace APIs. This is the primary function of the skill and involves standard operations like creating, retrieving, and updating forms. - [INDIRECT_PROMPT_INJECTION]: The skill provides the ability to read Google Forms and responses. Content from these external sources could potentially contain malicious instructions intended to influence the agent.
- Ingestion points: Data enters the agent's context through methods like
gws forms getandgws forms responses. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external form data as untrusted.
- Capability inventory: The agent can execute shell commands via the
gwsCLI and write to forms. - Sanitization: The skill does not implement specific sanitization of the retrieved form content before processing.
Audit Metadata