send-notification
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill accesses application-specific configuration files located in
~/.claude-marketing/. These files are used to enforce brand voice and compliance rules, which is consistent with the skill's purpose. - [SAFE]: Implements a human-in-the-loop approval mechanism (Step 7). The agent is instructed to present a preview of the message, mentions, and attachments for user confirmation before executing the delivery through the messaging platform.
- [SAFE]: Includes alert fatigue monitoring (Step 6), which checks recent notification history to prevent channel spamming, serving as a functional safety check.
Audit Metadata