notion-meeting-intelligence

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to connect to an external MCP endpoint at https://mcp.notion.com/mcp. This is an official domain for Notion, which is a well-known technology service.
  • [COMMAND_EXECUTION]: The workflow includes configuration commands for the codex CLI to add the Notion MCP, enable remote client features, and perform OAuth login. These are legitimate setup steps for the skill's environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from Notion documents via Notion:notion-fetch to assist in drafting agendas. This creates a potential surface for indirect prompt injection if the retrieved documents contain malicious instructions. The instructions do not specify explicit boundary markers or sanitization for this external content.
  • Ingestion points: Notion pages retrieved via Notion:notion-search and Notion:notion-fetch (SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: Page creation and updates via Notion:notion-create-pages and Notion:notion-update-page (SKILL.md)
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:19 AM
Security Audit — agent-trust-hub — notion-meeting-intelligence