The Agent Skills Directory

[SAFE]: The skill uses official Notion MCP endpoints (mcp.notion.com) and standard OAuth login procedures for authentication. These are well-known and trusted services for the intended functionality.
[SAFE]: The skill provides structured templates and guidelines in the reference/ directory to ensure consistent and high-quality research output. The use of <mention-page> tags for citations follows platform best practices.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize untrusted data from a Notion workspace via the notion-fetch tool.
Ingestion points: Data enters the context through Notion:notion-fetch in SKILL.md and various examples.
Boundary markers: The skill uses markdown headers and structured templates (e.g., reference/research-summary-template.md) to delimit findings, though it lacks explicit 'ignore instructions' markers for fetched content.
Capability inventory: The skill has the ability to write new content back to the workspace using Notion:notion-create-pages and Notion:notion-update-page.
Sanitization: There is no explicit evidence of content sanitization, but the workflow encourages human-in-the-loop confirmation of search results and final document drafting.

notion-research-documentation