notion-meeting-intelligence

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides setup instructions to add a Notion Model Context Protocol (MCP) server from the official URL https://mcp.notion.com/mcp.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external Notion pages, which presents a surface for indirect prompt injection.
  • Ingestion points: The skill fetches data using Notion:notion-search and Notion:notion-fetch as described in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or directions to treat the retrieved content as untrusted.
  • Capability inventory: The skill is capable of modifying Notion data using Notion:notion-create-pages and Notion:notion-update-page.
  • Sanitization: There is no evidence of content validation or sanitization for the data ingested from Notion.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:28 PM