notion-meeting-intelligence
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection surface. The skill fetches content from external Notion pages and uses it to generate meeting materials, which could allow malicious instructions within those pages to influence agent behavior.
- Ingestion points: Data retrieved from
Notion:notion-searchandNotion:notion-fetchinSKILL.md. - Boundary markers: Absent. The skill does not instruct the agent to ignore directives within the fetched content.
- Capability inventory: The skill can write and modify Notion pages via
Notion:notion-create-pagesandNotion:notion-update-page. - Sanitization: No validation or sanitization of the fetched data is performed before processing.
- [COMMAND_EXECUTION]: Provides instructions for the user to configure the Notion Model Context Protocol (MCP) using the official Notion service endpoint at
https://mcp.notion.com/mcp.
Audit Metadata