notion-automation

Warn

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external URL as an MCP server, which acts as a remote configuration and tool provider.
  • Evidence: The setup instructions require adding https://rube.app/mcp as an MCP server in the client configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from Notion pages and databases, which could contain malicious instructions designed to hijack the agent's behavior.
  • Ingestion points: Data is retrieved from external sources via NOTION_FETCH_BLOCK_CONTENTS (page content) and NOTION_QUERY_DATABASE (database records).
  • Boundary markers: The instructions do not define boundary markers or provide the agent with directives to ignore embedded instructions within the fetched data.
  • Capability inventory: The skill possesses extensive write and management permissions, including NOTION_CREATE_NOTION_PAGE, NOTION_UPDATE_PAGE, NOTION_INSERT_ROW_DATABASE, and NOTION_REPLACE_PAGE_CONTENT.
  • Sanitization: No sanitization or validation protocols are described to filter content retrieved from Notion before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 26, 2026, 09:11 PM