zoho-mail-health-check

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses email metadata including subjects and sender addresses to generate health reports. It requires sensitive API credentials such as Client Secrets and Refresh Tokens; however, it correctly directs users to manage these through environment variables rather than hardcoding them within the skill files.
  • [EXTERNAL_DOWNLOADS]: The fallback script utilizes the requests library to interact with well-known Zoho service domains (accounts.zoho.com and mail.zoho.com). These network operations are strictly limited to official service endpoints required for the skill's functionality.
  • [COMMAND_EXECUTION]: If the primary MCP tools are unavailable, the skill executes a locally provided Python script via the shell. This script is part of the skill's own reference documentation and performs standard API interactions.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted content from external email subjects and senders without explicit boundary markers. While this creates a potential vector for malicious content to be included in reports, the risk is inherent to mail-processing tasks and the skill's capabilities are scoped to health checking.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:39 PM
Security Audit — agent-trust-hub — zoho-mail-health-check