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
Risk Level
SAFE
Analyzed
May 20, 2026, 12:41 AM
Security Audit — agent-trust-hub — send-notification