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-fetch tool.
  • 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
Risk Level
SAFE
Analyzed
Aug 6, 2026, 04:52 PM
Security Audit — agent-trust-hub — notion-spec-to-implementation