spark-recipe-notification-hygiene

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses standard CLI commands for the Spark email client to manage notifications. All operations, such as listing unread notifications, reading threads, and reclassifying contacts, are consistent with legitimate inbox management workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data by reading email content via spark thread. While this introduces an indirect prompt injection surface, the skill's capabilities are restricted to email triage actions, and no unsafe interpolation of this data into shell execution or other high-privilege commands was identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:08 PM
Security Audit — agent-trust-hub — spark-recipe-notification-hygiene