notion
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a reference guide for performing standard CRUD operations (Create, Read, Update, Delete) on Notion workspaces using terminal commands.
- [EXTERNAL_DOWNLOADS]: All network operations are targeted at
api.notion.com. As Notion is a well-known service, these communications are considered safe and functional rather than suspicious. - [CREDENTIALS_UNSAFE]: The skill explicitly instructs the user to store their integration token in a local
.envfile (~/.clawg/.env). This is a standard and recommended security practice to avoid hardcoding secrets or exposing them in command history. - [PROMPT_INJECTION]: The skill's functionality to read Notion blocks (
GET /v1/blocks/{page_id}/children) introduces an indirect prompt injection surface. An agent processing this data could be influenced by instructions hidden within the fetched Notion content. However, this is an inherent risk of data-processing tools and no active malicious behavior is present in the skill's instructions.
Audit Metadata