notion-automate

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official Notion MCP tools (mcp__notion__search, mcp__notion__get_page, mcp__notion__query_database) for read-only workspace access, using standard OAuth-based authentication handled by the platform.
  • [SAFE]: The documentation in references/failure-modes.md includes high-quality security warnings regarding the risk of indirect prompt injection from Notion page content. The static analysis flag for 'ignore previous instructions' correctly identified these strings, but in context, they are used as examples in a security advisory meant to educate the user on how to handle untrusted input safely.
  • [SAFE]: No obfuscation, malicious command execution, or unauthorized network operations were detected. All external references target the official Notion service infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:06 PM
Security Audit — agent-trust-hub — notion-automate