notion-knowledge-capture

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to connect to the official Notion Model Context Protocol server at https://mcp.notion.com/mcp. This is a well-known service required for the skill's primary function of Notion integration and does not represent an unknown or untrusted source.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting untrusted conversation data and using it to influence Notion page content and metadata. 1. Ingestion points: Conversation context processed in Step 3 of the workflow (SKILL.md). 2. Boundary markers: Not present in the provided instructions to differentiate between conversation data and agent instructions. 3. Capability inventory: Powerful tools for searching, creating, and updating Notion pages (Notion:notion-search, Notion:notion-create-pages, Notion:notion-update-page). 4. Sanitization: No instructions exist to sanitize, validate, or escape the extracted conversation content before it is used to populate Notion database properties or page content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 01:22 PM
Security Audit — agent-trust-hub — notion-knowledge-capture