notion-mcp

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the @notionhq/notion-mcp package. This is the official package provided by Notion for Model Context Protocol integration.
  • [PROMPT_INJECTION]: The skill provides an indirect prompt injection surface by ingesting untrusted data from the Notion workspace (such as page content or comments).
  • Ingestion points: Data is pulled into the agent context via tools like notion-fetch, notion-search, and notion-get-comments in SKILL.md.
  • Boundary markers: Absent. There are no explicit instructions to the agent to ignore or delimit instructions found within fetched content.
  • Capability inventory: The skill includes several tools with write access, such as notion-create-pages, notion-update-page, and notion-create-database.
  • Sanitization: No specific sanitization, validation, or filtering of the fetched content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:57 AM
Security Audit — agent-trust-hub — notion-mcp