inbox-providers

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a comparison guide and architectural reference for email infrastructure tailored for AI agents.
  • [PROMPT_INJECTION]: The content explicitly addresses the risk of prompt injection through inbound emails and recommends using providers with built-in scanning and sanitization. No malicious injection instructions are present.
  • [EXTERNAL_DOWNLOADS]: The skill references legitimate CLI tools and SDKs (such as @molted/cli) associated with the described services, presented as standard installation examples.
  • [DATA_EXFILTRATION]: No patterns of data exfiltration or credential harvesting were found. The skill suggests best practices for isolating agent identities using subdomains and dedicated inboxes.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:38 PM
Security Audit — agent-trust-hub — inbox-providers