notion-automation

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires connection to a remote MCP server at https://rube.app/mcp to access the Notion toolset. This is a functional requirement for the toolkit integration.\n- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by retrieving data from external Notion sources that the agent then processes.\n
  • Ingestion points: Data enters the agent context through tools such as NOTION_SEARCH_NOTION_PAGE, NOTION_FETCH_DATABASE, NOTION_QUERY_DATABASE, and NOTION_FETCH_BLOCK_CONTENTS (SKILL.md).\n
  • Boundary markers: There are no instructions or delimiters provided to guide the agent to ignore or isolate instructions that may be present within retrieved Notion content.\n
  • Capability inventory: The agent is provided with powerful capabilities to modify the Notion environment, including NOTION_CREATE_NOTION_PAGE, NOTION_UPDATE_PAGE, NOTION_INSERT_ROW_DATABASE, and NOTION_CREATE_COMMENT (SKILL.md).\n
  • Sanitization: The skill does not include steps for validating or sanitizing retrieved Notion content before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 06:03 AM
Security Audit — agent-trust-hub — notion-automation