community-push-targeted
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust 'human-in-the-loop' pattern, explicitly requiring user confirmation before any tool invocation ('No automatic sends without user validation').
- [SAFE]: Tool invocations (e.g.,
classic_v1_create_push_notification,classic_v1_list_user) are used for their intended purpose of managing community notifications. - [SAFE]: Input validation is enforced within the instructions, such as character limits (<= 255) and rejection of placeholder content.
- [SAFE]: No evidence of data exfiltration, unauthorized file access, or remote code execution was found. The skill operates within the scope of a community management system.
Audit Metadata