notion-hello-world
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Notion API (such as page titles and content) which could theoretically contain malicious instructions if the connected Notion workspace contains untrusted content.
- Ingestion points: Data enters the agent's context through the
notion.searchandnotion.pages.retrievemethods shown inreferences/implementation.mdandreferences/examples.md. - Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the example code snippets.
- Capability inventory: The skill is configured with
Read,Write, andEdittools and utilizes the Notion API for search, creation, and retrieval operations. - Sanitization: Content retrieved from the API is processed and displayed without explicit validation or sanitization in these basic examples.
- [EXTERNAL_DOWNLOADS]: The skill references standard, official dependencies for interacting with the Notion service.
- Mentions the official
@notionhq/clientNode.js package and thenotion-clientPython package for API interaction.
Audit Metadata