skills/mukul975/anthropic-cybersecurity-skills/detecting-email-forwarding-rules-attack/Gen Agent Trust Hub
detecting-email-forwarding-rules-attack
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's scripts and documentation follow standard security auditing practices. The code is transparent, uses well-known libraries, and focuses on its stated defensive purpose without any hidden malicious functionality.- [EXTERNAL_DOWNLOADS]: The skill interacts with the Microsoft Graph API (
graph.microsoft.com) to retrieve mailbox rule configurations for auditing purposes. This is an interaction with a well-known service and is essential for the skill's primary function of detecting email-based threats.
Audit Metadata