portaly-email-mcp

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or behaviors were detected in the skill instructions. The skill focuses on its primary purpose of assisting with newsletter creation and management via official vendor tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes newsletter content (subject lines, HTML bodies, and placeholders) which could theoretically contain malicious instructions. However, this risk is effectively mitigated by a mandatory human-in-the-loop (HITL) requirement: the agent is instructed that nothing is sent until the creator manually reviews and approves the draft via a secure Portaly confirmation URL.
  • [EXTERNAL_DOWNLOADS]: The skill refers users to the official Portaly MCP server at https://portaly.cc/mcp. This is a vendor-owned resource necessary for the skill's core functionality.
  • [CREDENTIALS_UNSAFE]: The skill demonstrates safe credential handling by explicitly instructing users never to share authentication tokens in chat messages or committed files, directing them instead to use standard client configuration methods.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 02:49 AM