notion-mcp-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Notion workspaces which could contain malicious instructions.
- Ingestion points: The notion-search and notion-fetch tools ingest data from external Notion pages and databases (SKILL.md, references/usage-patterns.md).
- Boundary markers: The skill includes explicit instructions to require user confirmation before executing any create, update, or delete operations (SKILL.md).
- Capability inventory: The skill has the ability to create pages, update page properties, and add comments via notion-create-pages, notion-update-page, and notion-create-comment (references/usage-patterns.md).
- Sanitization: Safety is primarily maintained through human-in-the-loop confirmation and the use of the UXC CLI's JSON-envelope parsing.
Audit Metadata