notion-meeting-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONINGEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Notion pages which are considered untrusted sources. Malicious instructions embedded within these pages could influence the agent when generating meeting materials like agendas and pre-reads.
- Ingestion points: Retrieval of Notion content using
Notion:notion-fetchandNotion:notion-search. - Boundary markers: The instructions do not define delimiters or markers to separate fetched data from the agent's core instructions.
- Capability inventory: The skill possesses the ability to create and update Notion pages and comments via
Notion:notion-create-pagesandNotion:notion-update-page. - Sanitization: No specific data validation or sanitization is performed on ingested content.
- [METADATA_POISONING]: A discrepancy exists between the reported author name 'zapabob' and the 'Notion Labs, Inc.' copyright holder listed in the
LICENSE.txtfile. - [EXTERNAL_DOWNLOADS]: The skill includes setup instructions that direct the user to add an MCP server from the remote URL
https://mcp.notion.com/mcp, which is an official Notion service endpoint.
Audit Metadata