notion-research-documentation

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the Notion MCP server from the official mcp.notion.com domain.
  • [COMMAND_EXECUTION]: Setup involves executing commands like codex mcp add and codex --enable rmcp_client to configure the environment.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: Content is retrieved from Notion pages using Notion:notion-fetch. Boundary markers: There are no explicit delimiters or instructions to ignore embedded directives in the synthesis instructions. Capability inventory: The skill can create and update pages in the Notion workspace via Notion:notion-create-pages and Notion:notion-update-page. Sanitization: No sanitization or validation of fetched content is performed before synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:41 AM
Security Audit — agent-trust-hub — notion-research-documentation