notion-knowledge-capture

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and structure external conversation data into Notion pages via the Notion:notion-create-pages and Notion:notion-update-page tools. \n
  • Ingestion points: User-provided chat history and notes are extracted to form structured documentation such as FAQs, how-to guides, and decision records (SKILL.md). \n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data being processed. \n
  • Capability inventory: The skill uses a suite of Notion MCP tools (notion-search, notion-fetch, notion-create-pages, and notion-update-page) which modify the user's workspace. \n
  • Sanitization: There are no explicit instructions to sanitize or escape the content extracted from conversations before it is interpolated into the Notion page creation payload. \n- [COMMAND_EXECUTION]: The documentation includes platform-specific setup commands (codex mcp add notion --url https://mcp.notion.com/mcp) to enable the Notion MCP. This command references the official service endpoint and is part of the standard configuration workflow for the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:21 AM
Security Audit — agent-trust-hub — notion-knowledge-capture