notion-spec-to-implementation
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for connecting to the official Notion Model Context Protocol (MCP) at
https://mcp.notion.com/mcp. As this is a well-known service, the reference is considered safe. - [PROMPT_INJECTION]: The skill processes content from external Notion pages, which is an indirect prompt injection surface. The agent uses this data to populate implementation templates.
- Ingestion points: Data is ingested from Notion pages using the
Notion:notion-fetchtool. - Boundary markers: The workflow uses markdown templates and specific sections (e.g., clarified requirements, technical approach) to structure the agent's output.
- Capability inventory: The skill can search, read, create, and update pages within the user's Notion workspace.
- Sanitization: The skill relies on the agent's ability to parse and summarize text into predefined templates; it does not perform separate input sanitization.
Audit Metadata