recipe-create-feedback-form
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses established Google Workspace CLI tools (
gws) to perform tasks consistent with its description. No evidence of prompt injection, data exfiltration, or persistence mechanisms was found. - [COMMAND_EXECUTION]: Command execution is limited to predefined Google Workspace operations (
gws formsandgws gmail). The commands use static JSON payloads and parameters, posing no risk of command injection from untrusted sources. - [DATA_EXPOSURE_AND_EXFILTRATION]: While the skill interacts with network services, it does so through official vendor tooling (Google Workspace) to perform intended actions. No unauthorized access to local sensitive files (e.g., SSH keys, AWS credentials) was detected.
Audit Metadata