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-mcppackage. 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, andnotion-get-commentsinSKILL.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, andnotion-create-database. - Sanitization: No specific sanitization, validation, or filtering of the fetched content is described in the skill instructions.
Audit Metadata